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

Dataset: The Pile

Neuron 3241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.6045. Min Act: -0.0000

Data Index: 711855 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1271183 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1556553 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1996149 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1758246 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4279. Min Act: -0.0000

Data Index: 712458 (The Pile)

Max Activating Token Index: 1008

Text #6

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4031. Min Act: -0.0000

Data Index: 948512 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4164. Min Act: -0.0000

Data Index: 948906 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4090. Min Act: -0.0000

Data Index: 774707 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1356970 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4066. Min Act: -0.0000

Data Index: 597979 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1412413 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3759. Min Act: -0.0000

Data Index: 878847 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1641416 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3894. Min Act: -0.0000

Data Index: 3172 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1826805 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.4098. Min Act: -0.0000

Data Index: 636045 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1554385 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1474123 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 0.6045. Min Range: -0.6045

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1848480 (The Pile)

Max Activating Token Index: 923