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

Dataset: The Pile

Neuron 613 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.9792. Min Act: -0.0000

Data Index: 66714 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 5.1025. Min Range: -5.1025

Max Act: 5.0200. Min Act: -0.0000

Data Index: 1819193 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 5.1025. Min Range: -5.1025

Max Act: 5.1025. Min Act: -0.0000

Data Index: 535434 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.7106. Min Act: -0.0000

Data Index: 572782 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.4903. Min Act: -0.0000

Data Index: 691186 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.8702. Min Act: -0.0000

Data Index: 567329 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.6871. Min Act: -0.0000

Data Index: 1756644 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 5.1025. Min Range: -5.1025

Max Act: 3.7526. Min Act: -0.0000

Data Index: 650261 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 5.1025. Min Range: -5.1025

Max Act: 3.5813. Min Act: -0.0000

Data Index: 350931 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.3164. Min Act: -0.0000

Data Index: 1751022 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.8542. Min Act: -0.0000

Data Index: 1860407 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.0642. Min Act: -0.0000

Data Index: 136136 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 5.1025. Min Range: -5.1025

Max Act: 3.7621. Min Act: -0.0000

Data Index: 899593 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.4263. Min Act: -0.0000

Data Index: 1838993 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.2220. Min Act: -0.0000

Data Index: 1432667 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 5.1025. Min Range: -5.1025

Max Act: 3.9379. Min Act: -0.0000

Data Index: 1065542 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 5.1025. Min Range: -5.1025

Max Act: 3.6081. Min Act: -0.0000

Data Index: 701556 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.1844. Min Act: -0.0000

Data Index: 718069 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 5.1025. Min Range: -5.1025

Max Act: 3.7125. Min Act: -0.0000

Data Index: 824691 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 5.1025. Min Range: -5.1025

Max Act: 4.1922. Min Act: -0.0000

Data Index: 1553165 (The Pile)

Max Activating Token Index: 134