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

Dataset: The Pile

Neuron 669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1852091 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.6161. Min Act: -0.0000

Data Index: 956806 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1932473 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5388. Min Act: -0.0000

Data Index: 960864 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1997771 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1092995 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1574505 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1951895 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5554. Min Act: 0.0000

Data Index: 32428 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1434796 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4792. Min Act: -0.0000

Data Index: 867658 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5059. Min Act: -0.0000

Data Index: 539792 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1441643 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1131046 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4694. Min Act: 0.0000

Data Index: 1087615 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1781760 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4631. Min Act: -0.0000

Data Index: 375237 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4677. Min Act: -0.0000

Data Index: 180683 (The Pile)

Max Activating Token Index: 609

Text #18

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4310. Min Act: -0.0000

Data Index: 89768 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.9087. Min Range: -0.9087

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1393611 (The Pile)

Max Activating Token Index: 932