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

Dataset: The Pile

Neuron 3880 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: 0.2725. Min Range: -0.2725

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1553968 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2411. Min Act: -0.0000

Data Index: 327405 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2099. Min Act: -0.0000

Data Index: 23335 (The Pile)

Max Activating Token Index: 262

Text #3

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1594927 (The Pile)

Max Activating Token Index: 464

Text #4

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1697471 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2245. Min Act: -0.0000

Data Index: 905290 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2160. Min Act: -0.0000

Data Index: 889350 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1897. Min Act: -0.0000

Data Index: 824663 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1300676 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1994. Min Act: -0.0000

Data Index: 444536 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1639258 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2157. Min Act: -0.0000

Data Index: 490369 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2021. Min Act: -0.0000

Data Index: 730367 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1990. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2111. Min Act: -0.0000

Data Index: 229735 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.1966. Min Act: -0.0000

Data Index: 464695 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2029. Min Act: -0.0000

Data Index: 294585 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1970528 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2229. Min Act: -0.0000

Data Index: 627943 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.2725. Min Range: -0.2725

Max Act: 0.2032. Min Act: -0.0000

Data Index: 741360 (The Pile)

Max Activating Token Index: 130