Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0209. Min Act: -0.0006

Data Index: 773232 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0222. Min Act: -0.0006

Data Index: 264785 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0200. Min Act: -0.0005

Data Index: 1332627 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0186. Min Act: -0.0005

Data Index: 1253830 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0193. Min Act: -0.0005

Data Index: 345452 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0006

Data Index: 492017 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0198. Min Act: -0.0006

Data Index: 717608 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1094463 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0209. Min Act: -0.0005

Data Index: 282699 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0185. Min Act: -0.0006

Data Index: 367546 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1354871 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0188. Min Act: -0.0005

Data Index: 162930 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0200. Min Act: -0.0005

Data Index: 475759 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0193. Min Act: -0.0006

Data Index: 867697 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0185. Min Act: -0.0005

Data Index: 974735 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0184. Min Act: -0.0006

Data Index: 525590 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0187. Min Act: -0.0005

Data Index: 1047746 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0186. Min Act: -0.0005

Data Index: 124361 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0173. Min Act: -0.0006

Data Index: 456962 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0222. Min Range: -0.0222

Max Act: 0.0180. Min Act: -0.0006

Data Index: 816049 (C4 (Web Text))

Max Activating Token Index: 738