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

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

Neuron 628 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: 0.0190. Min Range: -0.0190

Max Act: 0.0190. Min Act: -0.0006

Data Index: 784418 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0177. Min Act: -0.0006

Data Index: 400514 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0179. Min Act: -0.0006

Data Index: 103469 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1172855 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0180. Min Act: -0.0005

Data Index: 104418 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0180. Min Act: -0.0006

Data Index: 752899 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1059035 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1051724 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0165. Min Act: -0.0006

Data Index: 496612 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0168. Min Act: -0.0006

Data Index: 526007 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0159. Min Act: -0.0006

Data Index: 462478 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0167. Min Act: -0.0006

Data Index: 673051 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0165. Min Act: -0.0006

Data Index: 612000 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0168. Min Act: -0.0006

Data Index: 764720 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1069669 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0167. Min Act: -0.0005

Data Index: 651600 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0157. Min Act: -0.0006

Data Index: 112344 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1028583 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0164. Min Act: -0.0005

Data Index: 266814 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0152. Min Act: -0.0006

Data Index: 95162 (C4 (Web Text))

Max Activating Token Index: 497