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

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

Neuron 1052 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0002

Data Index: 329313 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0186. Min Act: -0.0002

Data Index: 467050 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0189. Min Act: -0.0002

Data Index: 38849 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0189. Min Act: -0.0002

Data Index: 213155 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1045067 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0172. Min Act: -0.0002

Data Index: 629548 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0181. Min Act: -0.0002

Data Index: 655819 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0185. Min Act: -0.0002

Data Index: 583364 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1113990 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0174. Min Act: -0.0002

Data Index: 521823 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0165. Min Act: -0.0002

Data Index: 563479 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1580612 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0182. Min Act: -0.0002

Data Index: 639016 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0166. Min Act: -0.0002

Data Index: 459511 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0169. Min Act: -0.0002

Data Index: 671827 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0160. Min Act: -0.0002

Data Index: 83601 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0157. Min Act: -0.0002

Data Index: 506207 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1363411 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1208902 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0167. Min Act: -0.0002

Data Index: 949999 (C4 (Web Text))

Max Activating Token Index: 404