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

Dataset: The Pile

Neuron 2513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1441. Min Range: -1.1441

Max Act: 1.1441. Min Act: -0.0000

Data Index: 681261 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 1.1441. Min Range: -1.1441

Max Act: 1.1150. Min Act: -0.0000

Data Index: 605049 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8558. Min Act: -0.0000

Data Index: 770367 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8866. Min Act: -0.0000

Data Index: 177806 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1048167 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1577076 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1864909 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1111940 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1787670 (The Pile)

Max Activating Token Index: 939

Text #9

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7601. Min Act: -0.0000

Data Index: 520986 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8422. Min Act: -0.0000

Data Index: 900098 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8011. Min Act: -0.0000

Data Index: 58153 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7807. Min Act: -0.0000

Data Index: 524680 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7535. Min Act: -0.0000

Data Index: 365412 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.9191. Min Act: -0.0000

Data Index: 16641 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7509. Min Act: -0.0000

Data Index: 577258 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7895. Min Act: -0.0000

Data Index: 12918 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1135202 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1330000 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 1.1441. Min Range: -1.1441

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1693145 (The Pile)

Max Activating Token Index: 916