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

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

Neuron 4612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1523392 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1491375 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1551315 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1399796 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1508028 (Python Code)

Max Activating Token Index: 856

Text #5

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1623300 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1404385 (Python Code)

Max Activating Token Index: 331

Text #7

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1470807 (Python Code)

Max Activating Token Index: 362

Text #8

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1391431 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1596963 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1443058 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1478357 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1385105 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1654471 (Python Code)

Max Activating Token Index: 905

Text #14

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1640821 (Python Code)

Max Activating Token Index: 738

Text #15

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1549707 (Python Code)

Max Activating Token Index: 354

Text #16

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1368551 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1617735 (Python Code)

Max Activating Token Index: 749

Text #18

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1375994 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.4221. Min Range: -0.4221

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1530637 (Python Code)

Max Activating Token Index: 301