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

Dataset: The Pile

Neuron 647 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1004456 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1608097 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0995. Min Act: -0.0000

Data Index: 254428 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0880. Min Act: -0.0000

Data Index: 540442 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1185936 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0807. Min Act: -0.0000

Data Index: 448682 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1559582 (The Pile)

Max Activating Token Index: 403

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1508973 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1086603 (The Pile)

Max Activating Token Index: 774

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1546463 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0734. Min Act: -0.0000

Data Index: 764060 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1188944 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0794. Min Act: -0.0000

Data Index: 791089 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0845. Min Act: -0.0000

Data Index: 540146 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0818. Min Act: -0.0000

Data Index: 765426 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1469904 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0731. Min Act: -0.0000

Data Index: 679482 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1732114 (The Pile)

Max Activating Token Index: 991

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1286854 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1409612 (The Pile)

Max Activating Token Index: 293