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

Dataset: The Pile

Neuron 3274 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: 0.9368. Min Range: -0.9368

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1564422 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8429. Min Act: -0.0000

Data Index: 936411 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1541438 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8978. Min Act: -0.0000

Data Index: 405403 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1052666 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1976680 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1632620 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1849155 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8214. Min Act: -0.0000

Data Index: 21115 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8117. Min Act: -0.0000

Data Index: 341724 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1253372 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8324. Min Act: -0.0000

Data Index: 726003 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6868. Min Act: -0.0000

Data Index: 778681 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7434. Min Act: -0.0000

Data Index: 329665 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7891. Min Act: -0.0000

Data Index: 209233 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7856. Min Act: -0.0000

Data Index: 168045 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7761. Min Act: -0.0000

Data Index: 759950 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1590991 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1835819 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1772253 (The Pile)

Max Activating Token Index: 767