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

Dataset: The Pile

Neuron 2189 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: 1.4264. Min Range: -1.4264

Max Act: 1.3580. Min Act: -0.0000

Data Index: 377926 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.3860. Min Act: -0.0000

Data Index: 60910 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1944759 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.3693. Min Act: -0.0000

Data Index: 1963005 (The Pile)

Max Activating Token Index: 955

Text #4

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1375862 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.1369. Min Act: -0.0000

Data Index: 906588 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2137. Min Act: -0.0000

Data Index: 1020537 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2282. Min Act: -0.0000

Data Index: 953874 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.0948. Min Act: -0.0000

Data Index: 712736 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1990891 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1186415 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1541613 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.9985. Min Act: -0.0000

Data Index: 143106 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1224472 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.0526. Min Act: -0.0000

Data Index: 332461 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1924600 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1936515 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.0689. Min Act: -0.0000

Data Index: 622721 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.8122. Min Act: -0.0000

Data Index: 346728 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1044408 (The Pile)

Max Activating Token Index: 130