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

Dataset: The Pile

Neuron 3790 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: 0.3865. Min Range: -0.3865

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1885393 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3155. Min Act: -0.0000

Data Index: 552433 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2953. Min Act: -0.0001

Data Index: 677576 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2560. Min Act: -0.0000

Data Index: 130653 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3038. Min Act: -0.0000

Data Index: 980161 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1232766 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2705. Min Act: -0.0000

Data Index: 587639 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2273. Min Act: -0.0000

Data Index: 805216 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1967376 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1264057 (The Pile)

Max Activating Token Index: 664

Text #10

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2831. Min Act: -0.0000

Data Index: 979857 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2329. Min Act: -0.0000

Data Index: 162813 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1148744 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2265. Min Act: -0.0000

Data Index: 568663 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2397. Min Act: -0.0000

Data Index: 204954 (The Pile)

Max Activating Token Index: 862

Text #15

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2476. Min Act: -0.0000

Data Index: 61994 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1928589 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2035. Min Act: -0.0001

Data Index: 796224 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2524. Min Act: -0.0000

Data Index: 205269 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2742. Min Act: -0.0000

Data Index: 617090 (The Pile)

Max Activating Token Index: 100