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

Dataset: The Pile

Neuron 1235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0974. Min Act: -0.0002

Data Index: 144758 (The Pile)

Max Activating Token Index: 664

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1820286 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1026. Min Act: -0.0002

Data Index: 245511 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1639780 (The Pile)

Max Activating Token Index: 313

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0867. Min Act: -0.0002

Data Index: 694170 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1082133 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1001948 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1124534 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0931. Min Act: -0.0002

Data Index: 690091 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1059969 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0772. Min Act: -0.0002

Data Index: 940468 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1415286 (The Pile)

Max Activating Token Index: 809

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0811. Min Act: -0.0002

Data Index: 879389 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1383559 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0744. Min Act: -0.0002

Data Index: 510020 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0679. Min Act: -0.0002

Data Index: 950377 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0752. Min Act: -0.0002

Data Index: 432950 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1619408 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1074016 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0778. Min Act: -0.0002

Data Index: 414871 (The Pile)

Max Activating Token Index: 650