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

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

Neuron 3857 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: 0.0229. Min Range: -0.0229

Max Act: 0.0229. Min Act: -0.0003

Data Index: 538521 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0199. Min Act: -0.0003

Data Index: 463238 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0192. Min Act: -0.0003

Data Index: 464559 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0179. Min Act: -0.0003

Data Index: 224738 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0183. Min Act: -0.0003

Data Index: 860110 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1348895 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1114299 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1310164 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0181. Min Act: -0.0003

Data Index: 152702 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0164. Min Act: -0.0003

Data Index: 598633 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0173. Min Act: -0.0003

Data Index: 309679 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0171. Min Act: -0.0003

Data Index: 22161 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1253003 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0177. Min Act: -0.0003

Data Index: 58916 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1421848 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1157177 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0141. Min Act: -0.0003

Data Index: 908320 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0159. Min Act: -0.0003

Data Index: 416341 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0174. Min Act: -0.0003

Data Index: 267016 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0229. Min Range: -0.0229

Max Act: 0.0164. Min Act: -0.0003

Data Index: 6742 (C4 (Web Text))

Max Activating Token Index: 953