Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4658 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0002

Data Index: 827628 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1247126 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1222006 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0332. Min Act: -0.0002

Data Index: 902865 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0313. Min Act: -0.0002

Data Index: 942902 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0315. Min Act: -0.0002

Data Index: 590926 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0287. Min Act: -0.0002

Data Index: 154633 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1432836 (Python Code)

Max Activating Token Index: 298

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0307. Min Act: -0.0002

Data Index: 408904 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1187099 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0285. Min Act: -0.0002

Data Index: 954271 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0280. Min Act: -0.0002

Data Index: 396522 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0279. Min Act: -0.0002

Data Index: 271780 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0273. Min Act: -0.0002

Data Index: 425550 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1032932 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0258. Min Act: -0.0002

Data Index: 332145 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0272. Min Act: -0.0002

Data Index: 346732 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1145065 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1004239 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1150507 (C4 (Web Text))

Max Activating Token Index: 277