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

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

Neuron 4729 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: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1205033 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0347. Min Act: -0.0002

Data Index: 444859 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0320. Min Act: -0.0002

Data Index: 179141 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0306. Min Act: -0.0002

Data Index: 828853 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0331. Min Act: -0.0002

Data Index: 449428 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0283. Min Act: -0.0002

Data Index: 407013 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0291. Min Act: -0.0002

Data Index: 2210 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0287. Min Act: -0.0003

Data Index: 663925 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1289349 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0002

Data Index: 984408 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0002

Data Index: 206679 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0290. Min Act: -0.0002

Data Index: 575864 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1437011 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0245. Min Act: -0.0003

Data Index: 669062 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1111304 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1486480 (Python Code)

Max Activating Token Index: 627

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1509554 (Python Code)

Max Activating Token Index: 261

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1509232 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1534502 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0232. Min Act: -0.0002

Data Index: 516264 (C4 (Web Text))

Max Activating Token Index: 1017