Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 633 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0006

Data Index: 469862 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0213. Min Act: -0.0006

Data Index: 376271 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1178755 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1112004 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0201. Min Act: -0.0006

Data Index: 597503 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1330434 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0208. Min Act: -0.0006

Data Index: 667267 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0187. Min Act: -0.0006

Data Index: 337798 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0173. Min Act: -0.0006

Data Index: 536397 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1143396 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0167. Min Act: -0.0006

Data Index: 389958 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0155. Min Act: -0.0006

Data Index: 507153 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1198018 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0157. Min Act: -0.0006

Data Index: 545290 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0149. Min Act: -0.0006

Data Index: 92788 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0149. Min Act: -0.0006

Data Index: 564300 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0145. Min Act: -0.0006

Data Index: 332495 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0155. Min Act: -0.0006

Data Index: 141518 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0151. Min Act: -0.0006

Data Index: 819442 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0146. Min Act: -0.0006

Data Index: 864528 (C4 (Web Text))

Max Activating Token Index: 596