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

Dataset: The Pile

Neuron 3434 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0574. Min Range: -1.0574

Max Act: 1.0574. Min Act: -0.0000

Data Index: 465936 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8995. Min Act: -0.0000

Data Index: 503836 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1510363 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6177. Min Act: -0.0000

Data Index: 97670 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1062148 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7331. Min Act: -0.0000

Data Index: 404618 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1582870 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1623848 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1690940 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1856675 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6888. Min Act: -0.0000

Data Index: 587560 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6805. Min Act: -0.0000

Data Index: 100006 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.5751. Min Act: -0.0000

Data Index: 227983 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6037. Min Act: -0.0000

Data Index: 411093 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1139445 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1211435 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1881909 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.6369. Min Act: -0.0000

Data Index: 15468 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1495440 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1736727 (The Pile)

Max Activating Token Index: 282