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

Dataset: The Pile

Neuron 3767 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1326410 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0603. Min Act: -0.0000

Data Index: 168985 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1272796 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0572. Min Act: -0.0000

Data Index: 823335 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0542. Min Act: -0.0000

Data Index: 1393087 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1236032 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0489. Min Act: -0.0000

Data Index: 872710 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0545. Min Act: -0.0000

Data Index: 260940 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0549. Min Act: -0.0000

Data Index: 141701 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0500. Min Act: -0.0000

Data Index: 419098 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0495. Min Act: -0.0000

Data Index: 906968 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0451. Min Act: -0.0000

Data Index: 68050 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1847358 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1479817 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0468. Min Act: -0.0000

Data Index: 672279 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1849037 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0417. Min Act: -0.0000

Data Index: 108330 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0428. Min Act: -0.0000

Data Index: 149234 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0408. Min Act: -0.0000

Data Index: 884211 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0269. Min Act: -0.0000

Data Index: 347556 (The Pile)

Max Activating Token Index: 1015