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

Dataset: The Pile

Neuron 4158 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: 0.7195. Min Range: -0.7195

Max Act: 0.7195. Min Act: -0.0000

Data Index: 115160 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1048893 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1020990 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6158. Min Act: -0.0000

Data Index: 352044 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5387. Min Act: -0.0000

Data Index: 670502 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.6127. Min Act: -0.0000

Data Index: 965204 (The Pile)

Max Activating Token Index: 338

Text #6

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1251891 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5705. Min Act: -0.0000

Data Index: 127557 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1800509 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1920427 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1335153 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1500527 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5718. Min Act: -0.0000

Data Index: 902318 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.4987. Min Act: -0.0000

Data Index: 835102 (The Pile)

Max Activating Token Index: 1002

Text #14

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5531. Min Act: -0.0000

Data Index: 562108 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5536. Min Act: -0.0000

Data Index: 1948499 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1330025 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5292. Min Act: -0.0000

Data Index: 699532 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.4934. Min Act: -0.0000

Data Index: 402065 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 0.7195. Min Range: -0.7195

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1152369 (The Pile)

Max Activating Token Index: 510