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

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

Neuron 342 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1302347 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0456. Min Act: -0.0002

Data Index: 991202 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0300. Min Act: -0.0002

Data Index: 303538 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0378. Min Act: -0.0002

Data Index: 998873 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0429. Min Act: -0.0002

Data Index: 391717 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0355. Min Act: -0.0003

Data Index: 870751 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0332. Min Act: -0.0002

Data Index: 155601 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0358. Min Act: -0.0002

Data Index: 153346 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0360. Min Act: -0.0002

Data Index: 115853 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1498374 (Python Code)

Max Activating Token Index: 155

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1238318 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1131146 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0324. Min Act: -0.0002

Data Index: 314669 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0321. Min Act: -0.0002

Data Index: 900469 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0296. Min Act: -0.0002

Data Index: 972362 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0316. Min Act: -0.0002

Data Index: 79001 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0301. Min Act: -0.0002

Data Index: 591564 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1282252 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1178959 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0287. Min Act: -0.0002

Data Index: 302017 (C4 (Web Text))

Max Activating Token Index: 275