Project #2: LLM Visualization So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)

Dec 2, 2023 · 8:09 PM UTC

109
1,167
181
6,034
0
It also contains a walkthrough/guide of the steps, as well as a few interactive elements to play with. Why, you ask? For what purpose did I put all the time & effort into this project?
4
13
1
204
0
There's a real advantage to unpacking a set of abstractions, flattening them out. Abstractions can be useful for terseness and management, but they can be a real blocker to seeing the big picture.
3
5
112
With this, you can see the whole thing at once. You can see where the computation takes place, its complexity, and relative sizes of the tensors & weights.
1
18
4
180
0
The model with all the animations is tiiny, to make it tractable. For comparison, I threw in a few of the larger models (GPT-2, GPT-3), render-only. And when you see what it takes to just produce a single value in a mat-mul, the sheer scale of these things becomes apparent.
2
9
126
0
(Here's what goes into calculating a _single_ output value of a matrix-multiply)
2
7
96
0
What about understanding what each layer does? Uhh, sorry, won't be much help. The project just came out of "Let's build a 3D viz!", so the scope is a bit limited. It's more: here's a way to learn & digest the algorithm, and perhaps think about how to optimize the process.
1
3
67
As for what I got out of creating this: before I made it, I mostly knew how image convolution nets worked, but language-based models seemed kinda magical in comparison. Well, now I know them in a fair amount of detail!
1
2
54
I also learnt a good amount of GL (dF/dx, fwidth, ubos, instancing), and animation approaches. So, uhh, even if no-one sees this, the project definitely has some value to me.
3
3
58
Oh yeah, the link is here: bbycroft.net/llm/ Works best on desktop (sorry mobile). Left-click drag, right-click rotate, scroll to zoom. And hover over the tensor cells. Blue cells are weights/parameters, green cells are intermediate values. Each cell is a single number!
3
22
6
170
Well, I hope you find it interesting. Let me know your thoughts! And if someone makes it through the walkthrough and finds it a little ~incomplete towards the end I might even getting around to fix it (my attention has largely turned to other projects oops)
16
4
83
Short follow-up thread:
Brendan Bycroft
 @BrendanBycroft
8 Dec 2023
That's certainly been quite the response! 200k site visits, 1M X views, #1 on HN for a day or so, and plenty of very positive feedback. Here's a quick doc I put together with my sister a couple months ago, "setting expectations" I guess.
1
11
A technical guide to how I built it:
Brendan Bycroft
 @BrendanBycroft
8 Dec 2023
Here's a technical guide on how I wrote & structured some of the LLM Visualization. A few people have been asking about it, so I thought I'd write it up. Lots of code screenshots, so not for everyone.
1
6