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

Dataset: The Pile

Neuron 2523 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.8354. Min Act: -0.0000

Data Index: 1688483 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.7920. Min Act: -0.0000

Data Index: 597577 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.7551. Min Act: -0.0000

Data Index: 146189 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.7283. Min Act: -0.0000

Data Index: 1096590 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6893. Min Act: 0.0000

Data Index: 348681 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5902. Min Act: -0.0000

Data Index: 817864 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6339. Min Act: 0.0000

Data Index: 606711 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1289441 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6007. Min Act: -0.0000

Data Index: 943641 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5957. Min Act: -0.0000

Data Index: 928661 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6045. Min Act: -0.0000

Data Index: 840842 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6026. Min Act: -0.0000

Data Index: 879263 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1630975 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1649081 (The Pile)

Max Activating Token Index: 474

Text #14

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1707221 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6498. Min Act: -0.0000

Data Index: 1673121 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4550. Min Act: -0.0000

Data Index: 178760 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5381. Min Act: -0.0000

Data Index: 1188974 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5168. Min Act: -0.0000

Data Index: 574407 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5038. Min Act: -0.0000

Data Index: 25990 (The Pile)

Max Activating Token Index: 36