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

Dataset: The Pile

Neuron 4190 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3837. Min Act: -0.0000

Data Index: 723979 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3866. Min Act: -0.0000

Data Index: 671377 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1382224 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3492. Min Act: -0.0000

Data Index: 375724 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1323035 (The Pile)

Max Activating Token Index: 961

Text #5

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1734543 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1654321 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1550717 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3147. Min Act: -0.0000

Data Index: 831017 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3251. Min Act: -0.0000

Data Index: 643882 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1792611 (The Pile)

Max Activating Token Index: 65

Text #11

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1812526 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1276365 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3042. Min Act: -0.0000

Data Index: 748777 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1266211 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1853267 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.2961. Min Act: -0.0000

Data Index: 451134 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1565374 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1789543 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1891407 (The Pile)

Max Activating Token Index: 308