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

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

Neuron 1995 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0007

Data Index: 867279 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0203. Min Act: -0.0006

Data Index: 652810 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0007

Data Index: 1123020 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0196. Min Act: -0.0007

Data Index: 1167280 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0186. Min Act: -0.0006

Data Index: 591058 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0172. Min Act: -0.0007

Data Index: 1189298 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0180. Min Act: -0.0006

Data Index: 238322 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0174. Min Act: -0.0007

Data Index: 508587 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0176. Min Act: -0.0007

Data Index: 608839 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0176. Min Act: -0.0006

Data Index: 63165 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1087143 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0173. Min Act: -0.0006

Data Index: 815692 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0173. Min Act: -0.0006

Data Index: 382814 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0172. Min Act: -0.0007

Data Index: 826446 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0172. Min Act: -0.0007

Data Index: 1185753 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1196040 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0171. Min Act: -0.0007

Data Index: 115211 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0171. Min Act: -0.0006

Data Index: 915990 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0170. Min Act: -0.0006

Data Index: 649772 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1132172 (C4 (Web Text))

Max Activating Token Index: 4