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

Dataset: The Pile

Neuron 788 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0002

Data Index: 841017 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1006. Min Act: -0.0002

Data Index: 898495 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0966. Min Act: -0.0002

Data Index: 100907 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1426011 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1905326 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0914. Min Act: -0.0002

Data Index: 670766 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0897. Min Act: -0.0002

Data Index: 642704 (The Pile)

Max Activating Token Index: 676

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0909. Min Act: -0.0002

Data Index: 583344 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0919. Min Act: -0.0002

Data Index: 62111 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0893. Min Act: -0.0002

Data Index: 183411 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1608864 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0898. Min Act: -0.0002

Data Index: 691374 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0881. Min Act: -0.0002

Data Index: 465824 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0891. Min Act: -0.0002

Data Index: 276424 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1217827 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0860. Min Act: -0.0002

Data Index: 601841 (The Pile)

Max Activating Token Index: 930

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1698437 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1399118 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0891. Min Act: -0.0002

Data Index: 28715 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1617169 (The Pile)

Max Activating Token Index: 930