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

Dataset: The Pile

Neuron 4080 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: 1.7156. Min Range: -1.7156

Max Act: 1.7156. Min Act: -0.0000

Data Index: 208366 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.4080. Min Act: -0.0000

Data Index: 982800 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3194. Min Act: 0.0000

Data Index: 1678128 (The Pile)

Max Activating Token Index: 58

Text #3

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1115682 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3405. Min Act: -0.0000

Data Index: 532414 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.3785. Min Act: -0.0000

Data Index: 857677 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.2310. Min Act: -0.0000

Data Index: 461355 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.2140. Min Act: 0.0002

Data Index: 873375 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.1911. Min Act: -0.0000

Data Index: 735635 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1294719 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.2146. Min Act: -0.0000

Data Index: 610942 (The Pile)

Max Activating Token Index: 313

Text #11

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.1891. Min Act: -0.0000

Data Index: 1107640 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1150239 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1991034 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.0514. Min Act: -0.0000

Data Index: 1762264 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1054163 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.1043. Min Act: 0.0000

Data Index: 790056 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.0205. Min Act: -0.0000

Data Index: 198119 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1276660 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 1.7156. Min Range: -1.7156

Max Act: 1.0724. Min Act: -0.0000

Data Index: 377093 (The Pile)

Max Activating Token Index: 771