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

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

Neuron 400 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0497. Min Act: -0.0000

Data Index: 4636 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1185589 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1101717 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0434. Min Act: -0.0000

Data Index: 501577 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0417. Min Act: -0.0000

Data Index: 32136 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0409. Min Act: -0.0001

Data Index: 50739 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1109823 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0378. Min Act: -0.0000

Data Index: 355663 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1006553 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0372. Min Act: -0.0001

Data Index: 865478 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1252792 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0352. Min Act: 0.0000

Data Index: 249742 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1324022 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1604566 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0352. Min Act: -0.0000

Data Index: 857318 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0317. Min Act: -0.0000

Data Index: 251415 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1328893 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0350. Min Act: -0.0001

Data Index: 361366 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1156730 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0306. Min Act: -0.0001

Data Index: 379710 (C4 (Web Text))

Max Activating Token Index: 533