Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2012 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1098016 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1877535 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6884. Min Act: 0.0000

Data Index: 1810320 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6585. Min Act: 0.0000

Data Index: 1808237 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6189. Min Act: -0.0000

Data Index: 934334 (The Pile)

Max Activating Token Index: 149

Text #5

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6040. Min Act: 0.0001

Data Index: 715769 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1734411 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1885853 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1663448 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1490209 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5924. Min Act: -0.0000

Data Index: 764330 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6327. Min Act: -0.0000

Data Index: 397209 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.6041. Min Act: -0.0000

Data Index: 207367 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5670. Min Act: -0.0000

Data Index: 700395 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1702882 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1264706 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5756. Min Act: -0.0000

Data Index: 877833 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5513. Min Act: -0.0000

Data Index: 336770 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1129325 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.8714. Min Range: -0.8714

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1899188 (The Pile)

Max Activating Token Index: 525