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

Dataset: The Pile

Neuron 3662 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4277. Min Act: -0.0000

Data Index: 419385 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4437. Min Act: -0.0000

Data Index: 962481 (The Pile)

Max Activating Token Index: 326

Text #2

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1879459 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1485840 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1574525 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1429313 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1584414 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1794323 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1296564 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3578. Min Act: -0.0000

Data Index: 623444 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1715446 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1129974 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1071734 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1507181 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3198. Min Act: -0.0000

Data Index: 175073 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1190413 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1103506 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3242. Min Act: -0.0000

Data Index: 194448 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3660. Min Act: -0.0000

Data Index: 772477 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1736595 (The Pile)

Max Activating Token Index: 841