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

Dataset: The Pile

Neuron 2151 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7534. Min Act: -0.0000

Data Index: 701685 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1054816 (The Pile)

Max Activating Token Index: 357

Text #2

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7612. Min Act: -0.0000

Data Index: 529896 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6645. Min Act: -0.0000

Data Index: 549623 (The Pile)

Max Activating Token Index: 748

Text #4

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6534. Min Act: -0.0000

Data Index: 172834 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6710. Min Act: -0.0000

Data Index: 48597 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6540. Min Act: -0.0000

Data Index: 22035 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6221. Min Act: -0.0000

Data Index: 233676 (The Pile)

Max Activating Token Index: 687

Text #8

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6644. Min Act: -0.0000

Data Index: 571336 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1154532 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1199003 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6342. Min Act: -0.0000

Data Index: 510819 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6240. Min Act: 0.0000

Data Index: 922984 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5846. Min Act: -0.0000

Data Index: 173113 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1996602 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6027. Min Act: -0.0000

Data Index: 980881 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1207005 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6014. Min Act: -0.0000

Data Index: 72895 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5960. Min Act: -0.0000

Data Index: 995830 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1690031 (The Pile)

Max Activating Token Index: 493