Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4450 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0262. Min Act: -0.0003

Data Index: 986883 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0003

Data Index: 232288 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0262. Min Act: -0.0003

Data Index: 649209 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0264. Min Act: -0.0003

Data Index: 547554 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0263. Min Act: -0.0002

Data Index: 202061 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0251. Min Act: -0.0003

Data Index: 488280 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0249. Min Act: -0.0003

Data Index: 760684 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0256. Min Act: -0.0003

Data Index: 23078 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0249. Min Act: -0.0003

Data Index: 208891 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0235. Min Act: -0.0003

Data Index: 466767 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0245. Min Act: -0.0003

Data Index: 209337 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0247. Min Act: -0.0003

Data Index: 314476 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0246. Min Act: -0.0003

Data Index: 421274 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0003

Data Index: 740505 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1108866 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1130423 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0003

Data Index: 241078 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0244. Min Act: -0.0003

Data Index: 851064 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0231. Min Act: -0.0003

Data Index: 734970 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0228. Min Act: -0.0003

Data Index: 825510 (C4 (Web Text))

Max Activating Token Index: 326