Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1770 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0212. Min Act: -0.0003

Data Index: 365171 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1009046 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1203040 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0173. Min Act: -0.0003

Data Index: 626282 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0192. Min Act: -0.0003

Data Index: 419826 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0186. Min Act: -0.0003

Data Index: 491866 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1137692 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0174. Min Act: -0.0003

Data Index: 726948 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0182. Min Act: -0.0003

Data Index: 842960 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0189. Min Act: -0.0003

Data Index: 542653 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1029227 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0195. Min Act: -0.0003

Data Index: 731106 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1034547 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0169. Min Act: -0.0003

Data Index: 513703 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1246717 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0168. Min Act: -0.0003

Data Index: 665512 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1586297 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0151. Min Act: -0.0003

Data Index: 1034866 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0141. Min Act: -0.0003

Data Index: 40814 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.0227. Min Range: -0.0227

Max Act: 0.0176. Min Act: -0.0003

Data Index: 395527 (C4 (Web Text))

Max Activating Token Index: 646