Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1128 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0373. Min Act: -0.0002

Data Index: 849665 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0348. Min Act: -0.0002

Data Index: 704490 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0321. Min Act: -0.0002

Data Index: 111030 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0335. Min Act: -0.0002

Data Index: 3932 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0314. Min Act: -0.0002

Data Index: 222704 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0322. Min Act: -0.0002

Data Index: 717146 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0306. Min Act: -0.0002

Data Index: 30174 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1220619 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0306. Min Act: -0.0002

Data Index: 847141 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1121477 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0281. Min Act: -0.0002

Data Index: 250006 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0274. Min Act: -0.0002

Data Index: 340244 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0277. Min Act: -0.0002

Data Index: 902536 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0264. Min Act: -0.0002

Data Index: 117701 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1198624 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0262. Min Act: -0.0002

Data Index: 329296 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0267. Min Act: -0.0002

Data Index: 471242 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1209046 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0272. Min Act: -0.0002

Data Index: 321923 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1059180 (C4 (Web Text))

Max Activating Token Index: 386