Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3397 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1824497 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3420. Min Act: -0.0000

Data Index: 275076 (The Pile)

Max Activating Token Index: 575

Text #2

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1991870 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3702. Min Act: -0.0000

Data Index: 898543 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1900167 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1326297 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1636794 (The Pile)

Max Activating Token Index: 597

Text #7

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3055. Min Act: -0.0000

Data Index: 675900 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3373. Min Act: -0.0000

Data Index: 27360 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1612805 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1228151 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2583. Min Act: -0.0000

Data Index: 489732 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2845. Min Act: -0.0000

Data Index: 527348 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1918414 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2823. Min Act: -0.0000

Data Index: 826702 (The Pile)

Max Activating Token Index: 756

Text #15

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2736. Min Act: -0.0000

Data Index: 49764 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2795. Min Act: -0.0000

Data Index: 518397 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2784. Min Act: -0.0000

Data Index: 220558 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2695. Min Act: -0.0000

Data Index: 871881 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 0.3914. Min Range: -0.3914

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1386786 (The Pile)

Max Activating Token Index: 152