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

Dataset: The Pile

Neuron 3517 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: 0.7309. Min Range: -0.7309

Max Act: 0.7309. Min Act: -0.0000

Data Index: 371038 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6860. Min Act: -0.0000

Data Index: 676380 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6890. Min Act: -0.0000

Data Index: 865500 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1227938 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1767457 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1194088 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1477039 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6502. Min Act: -0.0000

Data Index: 356025 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1358668 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1272691 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1275223 (The Pile)

Max Activating Token Index: 907

Text #11

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6176. Min Act: -0.0000

Data Index: 292038 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1307256 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1851639 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1839384 (The Pile)

Max Activating Token Index: 40

Text #15

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1415414 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.6233. Min Act: -0.0000

Data Index: 206300 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5836. Min Act: -0.0000

Data Index: 129529 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5801. Min Act: -0.0000

Data Index: 140799 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 0.7309. Min Range: -0.7309

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1441381 (The Pile)

Max Activating Token Index: 824