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

Dataset: The Pile

Neuron 4835 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1979. Min Act: -0.0000

Data Index: 814006 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1220752 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.2072. Min Act: -0.0000

Data Index: 18206 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1883. Min Act: -0.0000

Data Index: 485915 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1225322 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1193955 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1890. Min Act: -0.0000

Data Index: 511230 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.2006. Min Act: -0.0000

Data Index: 848693 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1996. Min Act: -0.0000

Data Index: 554743 (The Pile)

Max Activating Token Index: 416

Text #9

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.2035. Min Act: -0.0000

Data Index: 373984 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1502353 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1532. Min Act: -0.0000

Data Index: 98089 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1670. Min Act: -0.0000

Data Index: 497379 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1857. Min Act: -0.0000

Data Index: 427548 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1368628 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1843. Min Act: -0.0000

Data Index: 582849 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1610026 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1720. Min Act: -0.0000

Data Index: 180030 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1281903 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1047034 (The Pile)

Max Activating Token Index: 63