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

Dataset: The Pile

Neuron 1891 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: 1.1279. Min Range: -1.1279

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1055567 (The Pile)

Max Activating Token Index: 298

Text #1

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1251529 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0368. Min Act: -0.0000

Data Index: 405013 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1216131 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.0646. Min Act: -0.0000

Data Index: 862921 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8642. Min Act: -0.0000

Data Index: 713120 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1463736 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7855. Min Act: -0.0000

Data Index: 78166 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7872. Min Act: -0.0000

Data Index: 264711 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8360. Min Act: -0.0000

Data Index: 342459 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8279. Min Act: -0.0000

Data Index: 178502 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1144998 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1491492 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1240118 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8029. Min Act: -0.0000

Data Index: 263863 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1522378 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1575644 (The Pile)

Max Activating Token Index: 188

Text #17

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1714519 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7659. Min Act: -0.0000

Data Index: 342695 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1666313 (The Pile)

Max Activating Token Index: 959