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

Dataset: The Pile

Neuron 1319 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: 0.7733. Min Range: -0.7733

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1198553 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1983793 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1961406 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1020117 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1014846 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5550. Min Act: -0.0000

Data Index: 845689 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1610493 (The Pile)

Max Activating Token Index: 814

Text #7

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5215. Min Act: -0.0000

Data Index: 187069 (The Pile)

Max Activating Token Index: 736

Text #8

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1832954 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5432. Min Act: -0.0000

Data Index: 787853 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5256. Min Act: -0.0000

Data Index: 908653 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5254. Min Act: -0.0000

Data Index: 909776 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1887513 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1132018 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1567148 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1849062 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1034253 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5155. Min Act: -0.0000

Data Index: 924568 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1180024 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1699396 (The Pile)

Max Activating Token Index: 158