Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 455 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0003

Data Index: 541762 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0333. Min Act: -0.0003

Data Index: 806091 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0315. Min Act: -0.0004

Data Index: 1407117 (Python Code)

Max Activating Token Index: 549

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0323. Min Act: -0.0004

Data Index: 934926 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0306. Min Act: -0.0004

Data Index: 1459705 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1549751 (Python Code)

Max Activating Token Index: 943

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1477705 (Python Code)

Max Activating Token Index: 699

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0327. Min Act: -0.0003

Data Index: 166450 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0293. Min Act: -0.0003

Data Index: 820915 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1625148 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1571135 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0292. Min Act: -0.0003

Data Index: 836261 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0313. Min Act: -0.0003

Data Index: 992584 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1224835 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1646297 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1028058 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0291. Min Act: -0.0003

Data Index: 13487 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1649478 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1582144 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1548333 (Python Code)

Max Activating Token Index: 130