Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1426 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.3447. Min Act: -0.0001

Data Index: 1617712 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1447796 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1586427 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2375. Min Act: -0.0001

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2441. Min Act: -0.0001

Data Index: 1248321 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2565. Min Act: -0.0000

Data Index: 657120 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1390497 (Python Code)

Max Activating Token Index: 529

Text #7

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2385. Min Act: -0.0000

Data Index: 783846 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2300. Min Act: -0.0001

Data Index: 558354 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2566. Min Act: -0.0000

Data Index: 268808 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1532377 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2202. Min Act: -0.0001

Data Index: 1367520 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1344755 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1403448 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2220. Min Act: -0.0000

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2341. Min Act: -0.0000

Data Index: 189425 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2194. Min Act: -0.0001

Data Index: 110128 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2204. Min Act: -0.0000

Data Index: 555230 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.3447. Min Range: -0.3447

Max Act: 0.2341. Min Act: -0.0001

Data Index: 231760 (C4 (Web Text))

Max Activating Token Index: 379