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

Dataset: The Pile

Neuron 3302 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: 0.8704. Min Range: -0.8704

Max Act: 0.8704. Min Act: -0.0000

Data Index: 44378 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.7123. Min Act: -0.0000

Data Index: 441759 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1930722 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1827577 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.6140. Min Act: -0.0000

Data Index: 759621 (The Pile)

Max Activating Token Index: 727

Text #5

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1922313 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1515301 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5967. Min Act: -0.0000

Data Index: 95623 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1663123 (The Pile)

Max Activating Token Index: 429

Text #9

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1792684 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.6309. Min Act: -0.0000

Data Index: 649968 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1637665 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5804. Min Act: -0.0000

Data Index: 550732 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1806943 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1776192 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5815. Min Act: -0.0000

Data Index: 680295 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5652. Min Act: -0.0000

Data Index: 449129 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5337. Min Act: -0.0000

Data Index: 548281 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1151884 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 0.8704. Min Range: -0.8704

Max Act: 0.5710. Min Act: -0.0000

Data Index: 925241 (The Pile)

Max Activating Token Index: 364