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

Dataset: The Pile

Neuron 3255 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: 1.1119. Min Range: -1.1119

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1638967 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.1119. Min Range: -1.1119

Max Act: 1.1119. Min Act: -0.0000

Data Index: 961386 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.9383. Min Act: -0.0000

Data Index: 871564 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1183719 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.7714. Min Act: -0.0000

Data Index: 292523 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8720. Min Act: -0.0000

Data Index: 580762 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1404143 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1630023 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1120990 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8738. Min Act: -0.0000

Data Index: 548933 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8228. Min Act: -0.0000

Data Index: 850259 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.7536. Min Act: -0.0000

Data Index: 388434 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.7686. Min Act: -0.0000

Data Index: 735275 (The Pile)

Max Activating Token Index: 957

Text #13

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8584. Min Act: -0.0000

Data Index: 113987 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1442819 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.7934. Min Act: -0.0000

Data Index: 129500 (The Pile)

Max Activating Token Index: 352

Text #16

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1478087 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1713861 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.7934. Min Act: -0.0000

Data Index: 328154 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 1.1119. Min Range: -1.1119

Max Act: 0.8125. Min Act: -0.0000

Data Index: 617383 (The Pile)

Max Activating Token Index: 203