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

Dataset: The Pile

Neuron 3778 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1126. Min Act: 0.0000

Data Index: 1521283 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.1016. Min Act: 0.0000

Data Index: 890123 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0995. Min Act: -0.0000

Data Index: 773832 (The Pile)

Max Activating Token Index: 76

Text #3

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0932. Min Act: 0.0000

Data Index: 1759282 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0886. Min Act: 0.0000

Data Index: 916401 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0854. Min Act: 0.0000

Data Index: 1466733 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0888. Min Act: 0.0000

Data Index: 1926297 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1686904 (The Pile)

Max Activating Token Index: 922

Text #8

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0768. Min Act: 0.0000

Data Index: 1804819 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0765. Min Act: 0.0000

Data Index: 1559876 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0737. Min Act: 0.0000

Data Index: 1109372 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0732. Min Act: 0.0000

Data Index: 1401223 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0729. Min Act: 0.0000

Data Index: 791196 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0718. Min Act: 0.0000

Data Index: 1883421 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0716. Min Act: 0.0000

Data Index: 513764 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0708. Min Act: 0.0000

Data Index: 776507 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0672. Min Act: 0.0000

Data Index: 1067399 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0661. Min Act: 0.0000

Data Index: 645182 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0664. Min Act: 0.0000

Data Index: 1781024 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 0.1126. Min Range: -0.1126

Max Act: 0.0661. Min Act: 0.0000

Data Index: 243900 (The Pile)

Max Activating Token Index: 543