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

Dataset: The Pile

Neuron 1976 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1251382 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.4748. Min Act: -0.0000

Data Index: 285075 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1879346 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1833379 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1041756 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1499276 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1571876 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.3071. Min Act: -0.0000

Data Index: 18018 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.3357. Min Act: -0.0000

Data Index: 454983 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2895. Min Act: -0.0000

Data Index: 573855 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1414104 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2662. Min Act: -0.0000

Data Index: 2630 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2848. Min Act: -0.0000

Data Index: 531015 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1067519 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1633467 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2717. Min Act: -0.0000

Data Index: 636049 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2537. Min Act: -0.0000

Data Index: 796931 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1070112 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2400. Min Act: -0.0000

Data Index: 480527 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 0.5185. Min Range: -0.5185

Max Act: 0.2174. Min Act: -0.0000

Data Index: 74969 (The Pile)

Max Activating Token Index: 311