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

Dataset: The Pile

Neuron 3932 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: 0.9798. Min Range: -0.9798

Max Act: 0.9798. Min Act: 0.0000

Data Index: 1829914 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.8348. Min Act: -0.0000

Data Index: 52366 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1461144 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7884. Min Act: -0.0000

Data Index: 769892 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.8100. Min Act: -0.0000

Data Index: 855707 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1304836 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7947. Min Act: -0.0000

Data Index: 647065 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7931. Min Act: -0.0000

Data Index: 203415 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1750659 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1981927 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7683. Min Act: -0.0000

Data Index: 576019 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1396670 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1593732 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.8159. Min Act: -0.0000

Data Index: 6903 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7918. Min Act: -0.0000

Data Index: 923255 (The Pile)

Max Activating Token Index: 645

Text #15

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1180346 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1981790 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1424866 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.7129. Min Act: -0.0000

Data Index: 625509 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 0.9798. Min Range: -0.9798

Max Act: 0.6889. Min Act: -0.0000

Data Index: 239073 (The Pile)

Max Activating Token Index: 178