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

Dataset: The Pile

Neuron 2673 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9979. Min Act: -0.0000

Data Index: 1789416 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.9223. Min Act: -0.0000

Data Index: 539835 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1635916 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1976877 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8625. Min Act: -0.0000

Data Index: 392316 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1580158 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1526303 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7718. Min Act: -0.0000

Data Index: 891548 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1731912 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1068713 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.8623. Min Act: -0.0000

Data Index: 406774 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1902786 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7857. Min Act: -0.0000

Data Index: 685676 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1558699 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7840. Min Act: -0.0000

Data Index: 649751 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7248. Min Act: -0.0000

Data Index: 56426 (The Pile)

Max Activating Token Index: 727

Text #16

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7546. Min Act: -0.0000

Data Index: 828496 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7738. Min Act: -0.0000

Data Index: 130112 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7443. Min Act: -0.0000

Data Index: 865853 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 0.9979. Min Range: -0.9979

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1654453 (The Pile)

Max Activating Token Index: 209