Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 704 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0003

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0003

Data Index: 957454 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0295. Min Act: -0.0003

Data Index: 272540 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0291. Min Act: -0.0003

Data Index: 191623 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1491274 (Python Code)

Max Activating Token Index: 787

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1393849 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1001015 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1200651 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0273. Min Act: -0.0003

Data Index: 81015 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1555540 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0244. Min Act: -0.0003

Data Index: 507050 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1054907 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1609905 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1410454 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1258670 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1544660 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1558662 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0239. Min Act: -0.0003

Data Index: 628796 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0249. Min Act: -0.0003

Data Index: 10991 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1510458 (Python Code)

Max Activating Token Index: 158