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

Dataset: The Pile

Neuron 3152 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: 0.7297. Min Range: -0.7297

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1220538 (The Pile)

Max Activating Token Index: 125

Text #1

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1627346 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6742. Min Act: -0.0000

Data Index: 164303 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1454024 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6311. Min Act: -0.0000

Data Index: 490923 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1018059 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6014. Min Act: -0.0000

Data Index: 998623 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1313810 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1716677 (The Pile)

Max Activating Token Index: 693

Text #9

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5247. Min Act: -0.0000

Data Index: 82802 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5151. Min Act: -0.0000

Data Index: 538507 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1995256 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1081564 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1557778 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1152554 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5056. Min Act: -0.0000

Data Index: 712704 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4982. Min Act: -0.0000

Data Index: 137970 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5131. Min Act: -0.0000

Data Index: 837986 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1335579 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1900629 (The Pile)

Max Activating Token Index: 198