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

Dataset: The Pile

Neuron 1345 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: 0.9041. Min Range: -0.9041

Max Act: 0.8438. Min Act: -0.0000

Data Index: 393075 (The Pile)

Max Activating Token Index: 817

Text #1

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1128853 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1443050 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.9041. Min Act: -0.0000

Data Index: 422772 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8269. Min Act: -0.0000

Data Index: 560584 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1835099 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7104. Min Act: -0.0000

Data Index: 80847 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8170. Min Act: -0.0000

Data Index: 176967 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8046. Min Act: -0.0000

Data Index: 863531 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7447. Min Act: -0.0000

Data Index: 456626 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1322370 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7827. Min Act: -0.0000

Data Index: 544989 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7623. Min Act: -0.0000

Data Index: 940650 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7845. Min Act: -0.0000

Data Index: 198465 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1824138 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7968. Min Act: -0.0000

Data Index: 737302 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1914914 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7194. Min Act: -0.0000

Data Index: 282510 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1560473 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1860236 (The Pile)

Max Activating Token Index: 127