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

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

Neuron 302 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: 0.0281. Min Range: -0.0281

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1166328 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0273. Min Act: -0.0006

Data Index: 572661 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0264. Min Act: -0.0006

Data Index: 979910 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1272410 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1302670 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1160847 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0256. Min Act: -0.0006

Data Index: 550167 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1142970 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0234. Min Act: -0.0006

Data Index: 346704 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1253234 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0259. Min Act: -0.0006

Data Index: 709322 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1256051 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0244. Min Act: -0.0006

Data Index: 175096 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0243. Min Act: -0.0005

Data Index: 803974 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0252. Min Act: -0.0006

Data Index: 676834 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1525595 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0235. Min Act: -0.0006

Data Index: 960994 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0242. Min Act: -0.0006

Data Index: 210132 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0237. Min Act: -0.0006

Data Index: 250306 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1013873 (C4 (Web Text))

Max Activating Token Index: 420