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

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

Neuron 1426 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: 1302808 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1583820 (Python Code)

Max Activating Token Index: 216

Text #2

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0345. Min Act: -0.0002

Data Index: 513582 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1389999 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1484718 (Python Code)

Max Activating Token Index: 442

Text #5

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1578150 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1384602 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0314. Min Act: -0.0002

Data Index: 217952 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1011658 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1454110 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1476966 (Python Code)

Max Activating Token Index: 639

Text #11

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1538947 (Python Code)

Max Activating Token Index: 1019

Text #12

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1230175 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0295. Min Act: -0.0002

Data Index: 733699 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1460810 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1511644 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0279. Min Act: -0.0002

Data Index: 409356 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1133362 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1451729 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0279. Min Act: -0.0002

Data Index: 840518 (C4 (Web Text))

Max Activating Token Index: 261