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

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

Neuron 1193 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0006

Data Index: 359598 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0190. Min Act: -0.0006

Data Index: 721612 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1238143 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0005

Data Index: 433275 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0166. Min Act: -0.0005

Data Index: 1146639 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0168. Min Act: -0.0006

Data Index: 681396 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0006

Data Index: 32227 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0006

Data Index: 559991 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0006

Data Index: 58729 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0006

Data Index: 68650 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0006

Data Index: 587338 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0158. Min Act: -0.0006

Data Index: 789033 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1041916 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0158. Min Act: -0.0005

Data Index: 943415 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0005

Data Index: 211442 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0005

Data Index: 995653 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0161. Min Act: -0.0005

Data Index: 1635942 (Python Code)

Max Activating Token Index: 700

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0161. Min Act: -0.0005

Data Index: 1103751 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0005

Data Index: 1018420 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0006

Data Index: 127178 (C4 (Web Text))

Max Activating Token Index: 966