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

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

Neuron 69 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0002

Data Index: 299158 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0273. Min Act: -0.0002

Data Index: 221465 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0255. Min Act: -0.0002

Data Index: 91694 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0247. Min Act: -0.0002

Data Index: 230218 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0254. Min Act: -0.0002

Data Index: 348977 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0238. Min Act: -0.0002

Data Index: 488184 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1198303 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1411730 (Python Code)

Max Activating Token Index: 930

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1569300 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1624815 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1165095 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0240. Min Act: -0.0002

Data Index: 729661 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1412610 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1284450 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1597374 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0234. Min Act: -0.0002

Data Index: 611788 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1482111 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0225. Min Act: -0.0002

Data Index: 372375 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0227. Min Act: -0.0002

Data Index: 772375 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0224. Min Act: -0.0002

Data Index: 382130 (C4 (Web Text))

Max Activating Token Index: 818