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

Dataset: The Pile

Neuron 3718 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: 0.8722. Min Range: -0.8722

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1074301 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7803. Min Act: -0.0000

Data Index: 647203 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7112. Min Act: -0.0000

Data Index: 407613 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7849. Min Act: -0.0000

Data Index: 887599 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7748. Min Act: -0.0000

Data Index: 61867 (The Pile)

Max Activating Token Index: 150

Text #5

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7030. Min Act: -0.0000

Data Index: 424426 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7877. Min Act: -0.0000

Data Index: 706602 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1306295 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1305684 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7273. Min Act: -0.0000

Data Index: 129461 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1112891 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1098321 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6713. Min Act: -0.0000

Data Index: 636523 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6684. Min Act: -0.0000

Data Index: 1604161 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6680. Min Act: -0.0000

Data Index: 692584 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6594. Min Act: -0.0000

Data Index: 419752 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1247003 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1998906 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1331926 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6714. Min Act: -0.0000

Data Index: 740233 (The Pile)

Max Activating Token Index: 200