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

Dataset: The Pile

Neuron 263 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: 0.8603. Min Range: -0.8603

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1135328 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.8168. Min Act: -0.0000

Data Index: 765366 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7271. Min Act: -0.0000

Data Index: 703027 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7273. Min Act: -0.0000

Data Index: 825850 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7326. Min Act: -0.0000

Data Index: 379060 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1575011 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1777793 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6447. Min Act: -0.0000

Data Index: 103741 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6571. Min Act: -0.0000

Data Index: 620711 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1819633 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6084. Min Act: -0.0000

Data Index: 244662 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5954. Min Act: -0.0000

Data Index: 586561 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5897. Min Act: -0.0000

Data Index: 705179 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1134237 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5724. Min Act: -0.0000

Data Index: 685447 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1444461 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5610. Min Act: -0.0000

Data Index: 951351 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1565181 (The Pile)

Max Activating Token Index: 646

Text #18

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5316. Min Act: -0.0000

Data Index: 712071 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5115. Min Act: -0.0000

Data Index: 266577 (The Pile)

Max Activating Token Index: 56