Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1183034 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0230. Min Act: -0.0003

Data Index: 318756 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0220. Min Act: -0.0003

Data Index: 896174 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0209. Min Act: -0.0003

Data Index: 108542 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0211. Min Act: -0.0003

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0187. Min Act: -0.0003

Data Index: 707941 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0194. Min Act: -0.0003

Data Index: 220275 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0189. Min Act: -0.0003

Data Index: 689294 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0194. Min Act: -0.0003

Data Index: 175131 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0183. Min Act: -0.0003

Data Index: 247574 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0185. Min Act: -0.0003

Data Index: 575050 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0177. Min Act: -0.0003

Data Index: 711847 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0182. Min Act: -0.0003

Data Index: 770299 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0180. Min Act: -0.0003

Data Index: 487922 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0178. Min Act: -0.0003

Data Index: 355698 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0178. Min Act: -0.0003

Data Index: 381502 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0172. Min Act: -0.0003

Data Index: 295984 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0161. Min Act: -0.0003

Data Index: 505311 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0194. Min Act: -0.0003

Data Index: 784404 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0163. Min Act: -0.0003

Data Index: 661387 (C4 (Web Text))

Max Activating Token Index: 295