Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2468 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1230926 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4111. Min Act: -0.0000

Data Index: 680273 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4228. Min Act: -0.0000

Data Index: 472126 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1228154 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1560354 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3888. Min Act: -0.0000

Data Index: 623643 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1112458 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1854045 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1772071 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4000. Min Act: -0.0000

Data Index: 479290 (The Pile)

Max Activating Token Index: 195

Text #10

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1541601 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3472. Min Act: -0.0000

Data Index: 619645 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1450744 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3646. Min Act: -0.0000

Data Index: 598626 (The Pile)

Max Activating Token Index: 484

Text #14

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1882770 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1921371 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3577. Min Act: -0.0000

Data Index: 598778 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3823. Min Act: -0.0000

Data Index: 937015 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1250472 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 0.4620. Min Range: -0.4620

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1587497 (The Pile)

Max Activating Token Index: 800