Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2031 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1428067 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.8141. Min Act: -0.0000

Data Index: 223786 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7422. Min Act: -0.0000

Data Index: 696235 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1799981 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1449963 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1986786 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6597. Min Act: -0.0000

Data Index: 677993 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6777. Min Act: -0.0000

Data Index: 399537 (The Pile)

Max Activating Token Index: 985

Text #8

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1602446 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6486. Min Act: -0.0000

Data Index: 796169 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.5899. Min Act: -0.0000

Data Index: 187755 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1618573 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6479. Min Act: -0.0000

Data Index: 659983 (The Pile)

Max Activating Token Index: 476

Text #13

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1770152 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.5951. Min Act: -0.0000

Data Index: 386482 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1045647 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.5845. Min Act: -0.0000

Data Index: 838900 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.5800. Min Act: -0.0000

Data Index: 848757 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1899011 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1247865 (The Pile)

Max Activating Token Index: 889