Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1114575 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0913. Min Act: -0.0002

Data Index: 286919 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0863. Min Act: -0.0002

Data Index: 197256 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0847. Min Act: -0.0002

Data Index: 46790 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0819. Min Act: -0.0002

Data Index: 767894 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1379140 (The Pile)

Max Activating Token Index: 595

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1392895 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1425702 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0833. Min Act: -0.0002

Data Index: 806377 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0792. Min Act: -0.0002

Data Index: 462815 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1401593 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0774. Min Act: -0.0002

Data Index: 248379 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1265637 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1053836 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1744421 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1664814 (The Pile)

Max Activating Token Index: 47

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0746. Min Act: -0.0002

Data Index: 532834 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1587651 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0730. Min Act: -0.0002

Data Index: 643995 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1459321 (The Pile)

Max Activating Token Index: 41