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

Dataset: The Pile

Neuron 4249 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.7910. Min Act: -0.0000

Data Index: 585842 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6915. Min Act: -0.0000

Data Index: 566933 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1848688 (The Pile)

Max Activating Token Index: 71

Text #3

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1083212 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6847. Min Act: -0.0000

Data Index: 331997 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1118074 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6465. Min Act: -0.0000

Data Index: 718944 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1405419 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1133643 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6618. Min Act: -0.0000

Data Index: 190812 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6159. Min Act: -0.0000

Data Index: 4369 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6138. Min Act: -0.0000

Data Index: 972472 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5655. Min Act: -0.0000

Data Index: 925016 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1520713 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1654447 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5877. Min Act: -0.0000

Data Index: 382516 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1921790 (The Pile)

Max Activating Token Index: 134

Text #17

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5857. Min Act: 0.0000

Data Index: 1159408 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5625. Min Act: -0.0000

Data Index: 767993 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1321832 (The Pile)

Max Activating Token Index: 55