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

Dataset: The Pile

Neuron 2690 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: 1.5562. Min Range: -1.5562

Max Act: 1.5562. Min Act: -0.0000

Data Index: 886150 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3714. Min Act: -0.0000

Data Index: 328395 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1088694 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2249. Min Act: -0.0000

Data Index: 364207 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2127. Min Act: -0.0000

Data Index: 404585 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1599620 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.3470. Min Act: -0.0000

Data Index: 276089 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2957. Min Act: -0.0000

Data Index: 924691 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2391. Min Act: -0.0000

Data Index: 512292 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1280261 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.0498. Min Act: -0.0000

Data Index: 292953 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2103. Min Act: -0.0000

Data Index: 270269 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1577. Min Act: -0.0000

Data Index: 671782 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2805. Min Act: -0.0000

Data Index: 1923100 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1549667 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1645094 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1779407 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1076032 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1494005 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 1.5562. Min Range: -1.5562

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1703535 (The Pile)

Max Activating Token Index: 441