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

Dataset: The Pile

Neuron 2068 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1204787 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5494. Min Act: -0.0000

Data Index: 796457 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1290023 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1137703 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4894. Min Act: -0.0000

Data Index: 23112 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5689. Min Act: -0.0000

Data Index: 113847 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5124. Min Act: -0.0000

Data Index: 303448 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5106. Min Act: -0.0000

Data Index: 534360 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1756357 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5158. Min Act: -0.0000

Data Index: 746992 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1572652 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.5050. Min Act: -0.0000

Data Index: 275340 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4800. Min Act: -0.0000

Data Index: 842572 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4834. Min Act: -0.0000

Data Index: 763173 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4779. Min Act: -0.0000

Data Index: 122756 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4676. Min Act: -0.0000

Data Index: 91549 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4472. Min Act: -0.0000

Data Index: 557236 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1557131 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4374. Min Act: -0.0000

Data Index: 715000 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 0.5889. Min Range: -0.5889

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1134698 (The Pile)

Max Activating Token Index: 385