Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 399 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0313. Min Act: -0.0001

Data Index: 657238 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0341. Min Act: -0.0001

Data Index: 476290 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1046712 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0332. Min Act: -0.0002

Data Index: 645719 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0313. Min Act: -0.0001

Data Index: 249719 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0306. Min Act: -0.0002

Data Index: 477003 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0268. Min Act: -0.0002

Data Index: 87246 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0271. Min Act: -0.0001

Data Index: 137570 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1051005 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1523194 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0291. Min Act: -0.0001

Data Index: 807799 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0277. Min Act: -0.0001

Data Index: 332306 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0282. Min Act: -0.0002

Data Index: 670316 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1139967 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1565078 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1102682 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1595313 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0264. Min Act: -0.0002

Data Index: 37638 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0258. Min Act: -0.0001

Data Index: 551218 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.0341. Min Range: -0.0341

Max Act: 0.0236. Min Act: -0.0001

Data Index: 1328456 (C4 (Web Text))

Max Activating Token Index: 806