https://colab.research.google.com/drive/1F5SoDy1JPvZe5lf6dnGHSkB4C6vPIFcW?usp=sh...
Duno why we didn't end up linking the colab.
Here it is anyway in case anyone is interested.
I might fix some things and make a pull request to add it to transformer lens later if Neel thinks that's a good idea.
Maybe modifying the original neuroscope so it has a selector to change between showing layers and showing an specific Neurons would be better idea though .
Also about speed, it's not that bad.
It still takes a moment to load in colab wich can be anoying but it was still usable. (And for whatever reason it was near instant when Alex ran the notebook locally)
That said we were trying whith gpt small maybe it's worse whith bigger models.