Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1152 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0003

Data Index: 808527 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0222. Min Act: -0.0002

Data Index: 885172 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0206. Min Act: -0.0003

Data Index: 489279 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0204. Min Act: -0.0003

Data Index: 428187 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0196. Min Act: -0.0003

Data Index: 857182 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0172. Min Act: -0.0003

Data Index: 752969 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0172. Min Act: -0.0002

Data Index: 236612 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0180. Min Act: -0.0003

Data Index: 469069 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0175. Min Act: -0.0002

Data Index: 329751 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0176. Min Act: -0.0003

Data Index: 161454 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0175. Min Act: -0.0003

Data Index: 404756 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0162. Min Act: -0.0002

Data Index: 226064 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0170. Min Act: -0.0003

Data Index: 90701 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1227500 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0166. Min Act: -0.0003

Data Index: 674869 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1208559 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0164. Min Act: -0.0002

Data Index: 415717 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0163. Min Act: -0.0002

Data Index: 170376 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0166. Min Act: -0.0003

Data Index: 489398 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0168. Min Act: -0.0002

Data Index: 537157 (C4 (Web Text))

Max Activating Token Index: 481