Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 621 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0006

Data Index: 272532 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0198. Min Act: -0.0006

Data Index: 249221 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0196. Min Act: -0.0006

Data Index: 159487 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1270899 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0193. Min Act: -0.0006

Data Index: 992985 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1278045 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0178. Min Act: -0.0006

Data Index: 559711 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1265404 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1052522 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0174. Min Act: -0.0006

Data Index: 4810 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0166. Min Act: -0.0006

Data Index: 936409 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1220692 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0168. Min Act: -0.0006

Data Index: 669968 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1139735 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0174. Min Act: -0.0006

Data Index: 485823 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0177. Min Act: -0.0006

Data Index: 770562 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0168. Min Act: -0.0006

Data Index: 118242 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0170. Min Act: -0.0006

Data Index: 200482 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0166. Min Act: -0.0006

Data Index: 897723 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0165. Min Act: -0.0006

Data Index: 730622 (C4 (Web Text))

Max Activating Token Index: 984