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

Dataset: The Pile

Neuron 1879 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.4468. Min Act: -0.0000

Data Index: 245939 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.2742. Min Act: -0.0000

Data Index: 619024 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.2626. Min Act: -0.0000

Data Index: 987287 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 1.4468. Min Range: -1.4468

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1804713 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1711. Min Act: -0.0000

Data Index: 673693 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1652882 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1091309 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1493. Min Act: -0.0000

Data Index: 909142 (The Pile)

Max Activating Token Index: 319

Text #8

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1790. Min Act: -0.0000

Data Index: 334508 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1058046 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1837462 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1918445 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0859. Min Act: -0.0000

Data Index: 319876 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0783. Min Act: -0.0000

Data Index: 902761 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1606046 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.1034. Min Act: -0.0000

Data Index: 658137 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1906816 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1584018 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.4468. Min Range: -1.4468

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1936788 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 1.4468. Min Range: -1.4468

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1693629 (The Pile)

Max Activating Token Index: 662