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

Dataset: The Pile

Neuron 2693 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.4454. Min Act: -0.0000

Data Index: 628809 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1400927 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1945942 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1743236 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3176. Min Act: -0.0000

Data Index: 951900 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1789680 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1414606 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2890. Min Act: -0.0000

Data Index: 864496 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1816027 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1517367 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1265769 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2968. Min Act: -0.0000

Data Index: 607177 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1813898 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2516. Min Act: -0.0000

Data Index: 100379 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2750. Min Act: -0.0000

Data Index: 130754 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.3036. Min Act: -0.0000

Data Index: 124017 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1248940 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1980839 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1199309 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 0.4454. Min Range: -0.4454

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1272312 (The Pile)

Max Activating Token Index: 903