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

Dataset: The Pile

Neuron 768 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: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1572730 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1835289 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1111085 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0635. Min Act: -0.0000

Data Index: 527749 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0683. Min Act: -0.0000

Data Index: 376384 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1043865 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1534640 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1817107 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1737900 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0603. Min Act: -0.0000

Data Index: 284440 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0560. Min Act: -0.0000

Data Index: 239979 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0600. Min Act: -0.0000

Data Index: 135322 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1513993 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1472048 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0547. Min Act: -0.0000

Data Index: 48107 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1563626 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1695985 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0513. Min Act: -0.0000

Data Index: 416680 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1727643 (The Pile)

Max Activating Token Index: 541

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1556121 (The Pile)

Max Activating Token Index: 496