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

Dataset: The Pile

Neuron 3927 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1057. Min Range: -1.1057

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1122436 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 1.1057. Min Range: -1.1057

Max Act: 1.0953. Min Act: -0.0000

Data Index: 27454 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8783. Min Act: -0.0000

Data Index: 936198 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1290846 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 1.1057. Min Range: -1.1057

Max Act: 1.0380. Min Act: -0.0000

Data Index: 22782 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1444328 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1734659 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7076. Min Act: -0.0000

Data Index: 798564 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8086. Min Act: -0.0000

Data Index: 871810 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7081. Min Act: -0.0000

Data Index: 647131 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1459219 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1556695 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7197. Min Act: -0.0000

Data Index: 143047 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1529738 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1114660 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6914. Min Act: -0.0000

Data Index: 442789 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7897. Min Act: -0.0000

Data Index: 732125 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6499. Min Act: -0.0000

Data Index: 359427 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1793174 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7579. Min Act: -0.0000

Data Index: 301740 (The Pile)

Max Activating Token Index: 1009