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

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

Neuron 3003 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: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1458091 (Python Code)

Max Activating Token Index: 143

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0365. Min Act: -0.0002

Data Index: 920400 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1597267 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0319. Min Act: -0.0002

Data Index: 763397 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1530397 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1521282 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1488566 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1525582 (Python Code)

Max Activating Token Index: 229

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1392485 (Python Code)

Max Activating Token Index: 253

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1405982 (Python Code)

Max Activating Token Index: 1004

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1559312 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1580899 (Python Code)

Max Activating Token Index: 906

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1650243 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0316. Min Act: -0.0002

Data Index: 407677 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1511439 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1587689 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1368979 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1442828 (Python Code)

Max Activating Token Index: 296

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0288. Min Act: -0.0002

Data Index: 611462 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1631371 (Python Code)

Max Activating Token Index: 960