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

Dataset: The Pile

Neuron 3524 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: 0.4469. Min Range: -0.4469

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1803942 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.4149. Min Act: -0.0000

Data Index: 859608 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1733351 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1851251 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3892. Min Act: -0.0000

Data Index: 63713 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3853. Min Act: -0.0000

Data Index: 809947 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3799. Min Act: -0.0000

Data Index: 579864 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3681. Min Act: -0.0000

Data Index: 93489 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1058250 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1968124 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3487. Min Act: -0.0000

Data Index: 544996 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3534. Min Act: -0.0000

Data Index: 370 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1820447 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3722. Min Act: -0.0000

Data Index: 149969 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3352. Min Act: -0.0000

Data Index: 462728 (The Pile)

Max Activating Token Index: 903

Text #15

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3417. Min Act: -0.0000

Data Index: 208734 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1921328 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1813953 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1932643 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.4469. Min Range: -0.4469

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1182013 (The Pile)

Max Activating Token Index: 532