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

Dataset: The Pile

Neuron 2021 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.8631. Min Act: -0.0000

Data Index: 176853 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1819565 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.6057. Min Act: -0.0000

Data Index: 407418 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3205. Min Act: -0.0000

Data Index: 1178730 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1094391 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2036. Min Act: -0.0000

Data Index: 627652 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.3320. Min Act: -0.0000

Data Index: 200505 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.1725. Min Act: -0.0000

Data Index: 737039 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2241. Min Act: -0.0000

Data Index: 1045053 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2829. Min Act: -0.0000

Data Index: 210640 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2758. Min Act: -0.0000

Data Index: 923807 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1479607 (The Pile)

Max Activating Token Index: 959

Text #12

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2066. Min Act: -0.0000

Data Index: 704428 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1427345 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.1620. Min Act: -0.0000

Data Index: 527816 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1548750 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 1.8631. Min Range: -1.8631

Max Act: 0.9732. Min Act: -0.0000

Data Index: 43291 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2299. Min Act: -0.0000

Data Index: 427685 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.2653. Min Act: -0.0000

Data Index: 990903 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.8631. Min Range: -1.8631

Max Act: 1.0906. Min Act: -0.0000

Data Index: 316395 (The Pile)

Max Activating Token Index: 348