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

Dataset: The Pile

Neuron 1893 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: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: -0.0000

Data Index: 927789 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1694029 (The Pile)

Max Activating Token Index: 711

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1083869 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5695. Min Act: -0.0000

Data Index: 41876 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4926. Min Act: -0.0000

Data Index: 95674 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4869. Min Act: -0.0000

Data Index: 194363 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1601235 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4653. Min Act: -0.0000

Data Index: 162900 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4984. Min Act: -0.0000

Data Index: 551561 (The Pile)

Max Activating Token Index: 923

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4630. Min Act: -0.0000

Data Index: 929990 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1627779 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4737. Min Act: -0.0000

Data Index: 714745 (The Pile)

Max Activating Token Index: 907

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1403055 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1959148 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1130692 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4840. Min Act: -0.0000

Data Index: 179462 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4983. Min Act: -0.0000

Data Index: 857756 (The Pile)

Max Activating Token Index: 915

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1562451 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1240652 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4323. Min Act: -0.0000

Data Index: 900095 (The Pile)

Max Activating Token Index: 919