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

Dataset: The Pile

Neuron 3469 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.6628. Min Act: -0.0000

Data Index: 989047 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2790. Min Act: -0.0000

Data Index: 646119 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2941. Min Act: -0.0001

Data Index: 213081 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3286. Min Act: -0.0000

Data Index: 545743 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3252. Min Act: -0.0000

Data Index: 516999 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1982623 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2612. Min Act: -0.0000

Data Index: 930385 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1161461 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1066615 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2794. Min Act: -0.0000

Data Index: 797770 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1014223 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1563375 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1888105 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1727142 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2607. Min Act: -0.0000

Data Index: 285419 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2537. Min Act: -0.0000

Data Index: 741921 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1988380 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2523. Min Act: -0.0000

Data Index: 987617 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1279605 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 0.6628. Min Range: -0.6628

Max Act: 0.2393. Min Act: -0.0000

Data Index: 65595 (The Pile)

Max Activating Token Index: 823