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

Dataset: The Pile

Neuron 4466 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: 1.1659. Min Range: -1.1659

Max Act: 1.1659. Min Act: -0.0000

Data Index: 700435 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1016. Min Act: -0.0000

Data Index: 763437 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1509807 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1122412 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9993. Min Act: -0.0000

Data Index: 495912 (The Pile)

Max Activating Token Index: 35

Text #5

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1879519 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8877. Min Act: -0.0000

Data Index: 971715 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8864. Min Act: -0.0000

Data Index: 463675 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0121. Min Act: -0.0000

Data Index: 412698 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1353569 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8609. Min Act: -0.0000

Data Index: 392784 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1813545 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9725. Min Act: -0.0000

Data Index: 664722 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1768122 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1833412 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8852. Min Act: -0.0000

Data Index: 43431 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1033240 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9019. Min Act: -0.0000

Data Index: 796948 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8183. Min Act: -0.0000

Data Index: 992307 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8379. Min Act: -0.0000

Data Index: 65731 (The Pile)

Max Activating Token Index: 197