Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1521 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1276362 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1348319 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0199. Min Act: -0.0002

Data Index: 566230 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1014148 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0186. Min Act: -0.0002

Data Index: 493684 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0179. Min Act: -0.0002

Data Index: 184245 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1026392 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0178. Min Act: -0.0002

Data Index: 479752 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0176. Min Act: -0.0002

Data Index: 91378 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0178. Min Act: -0.0002

Data Index: 76937 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1233297 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0173. Min Act: -0.0002

Data Index: 894679 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0180. Min Act: -0.0002

Data Index: 297026 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0171. Min Act: -0.0002

Data Index: 20844 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0168. Min Act: -0.0002

Data Index: 289513 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0167. Min Act: -0.0002

Data Index: 558754 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0167. Min Act: -0.0002

Data Index: 760458 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0171. Min Act: -0.0002

Data Index: 445743 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0173. Min Act: -0.0002

Data Index: 366117 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0169. Min Act: -0.0002

Data Index: 261006 (C4 (Web Text))

Max Activating Token Index: 60