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

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

Neuron 1488 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1166589 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0213. Min Act: -0.0006

Data Index: 318176 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0217. Min Act: -0.0006

Data Index: 382439 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0205. Min Act: -0.0006

Data Index: 546867 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1299845 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0191. Min Act: -0.0006

Data Index: 361460 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0193. Min Act: -0.0006

Data Index: 61308 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0190. Min Act: -0.0006

Data Index: 245256 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1100501 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1325034 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1346491 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1208330 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0172. Min Act: -0.0006

Data Index: 561587 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0174. Min Act: -0.0006

Data Index: 265846 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0174. Min Act: -0.0006

Data Index: 234997 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0174. Min Act: -0.0006

Data Index: 465909 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0169. Min Act: -0.0006

Data Index: 584199 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0168. Min Act: -0.0006

Data Index: 671269 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1043464 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1231763 (C4 (Web Text))

Max Activating Token Index: 332