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

Dataset: The Pile

Neuron 1576 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1998826 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1509799 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1339600 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5252. Min Act: -0.0000

Data Index: 869898 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1002749 (The Pile)

Max Activating Token Index: 859

Text #5

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4839. Min Act: -0.0000

Data Index: 799332 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4857. Min Act: -0.0000

Data Index: 491855 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.3652. Min Act: -0.0000

Data Index: 259844 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4386. Min Act: -0.0000

Data Index: 296736 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4960. Min Act: -0.0000

Data Index: 526095 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4579. Min Act: -0.0000

Data Index: 721292 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4507. Min Act: -0.0000

Data Index: 667994 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1189777 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4507. Min Act: -0.0000

Data Index: 669068 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.3799. Min Act: -0.0000

Data Index: 129622 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.3805. Min Act: -0.0000

Data Index: 235505 (The Pile)

Max Activating Token Index: 642

Text #16

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4233. Min Act: -0.0000

Data Index: 358882 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.3858. Min Act: -0.0000

Data Index: 615457 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.3663. Min Act: -0.0000

Data Index: 991461 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.3745. Min Act: -0.0000

Data Index: 974885 (The Pile)

Max Activating Token Index: 682