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

Dataset: The Pile

Neuron 3778 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: 0.8862. Min Range: -0.8862

Max Act: 0.8862. Min Act: -0.0000

Data Index: 229611 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1077198 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5899. Min Act: -0.0000

Data Index: 285088 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1751816 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1809358 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6496. Min Act: -0.0000

Data Index: 900336 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5909. Min Act: -0.0000

Data Index: 614286 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1895516 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1831379 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5875. Min Act: -0.0000

Data Index: 501125 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5775. Min Act: -0.0000

Data Index: 109625 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1789821 (The Pile)

Max Activating Token Index: 806

Text #12

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1180672 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5603. Min Act: -0.0000

Data Index: 822389 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1873859 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5414. Min Act: -0.0000

Data Index: 468704 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5086. Min Act: -0.0000

Data Index: 705723 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1441011 (The Pile)

Max Activating Token Index: 48

Text #18

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5531. Min Act: -0.0000

Data Index: 193563 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1300575 (The Pile)

Max Activating Token Index: 973