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

Dataset: The Pile

Neuron 1771 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: 1.1009. Min Range: -1.1009

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1556293 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1156030 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.9368. Min Act: -0.0000

Data Index: 997787 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1692029 (The Pile)

Max Activating Token Index: 730

Text #4

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.7695. Min Act: -0.0000

Data Index: 524027 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.7645. Min Act: -0.0000

Data Index: 513656 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1420262 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1345855 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1412073 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1602104 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6600. Min Act: -0.0000

Data Index: 121171 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6572. Min Act: -0.0000

Data Index: 56603 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6742. Min Act: -0.0000

Data Index: 859924 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6528. Min Act: -0.0000

Data Index: 825286 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6179. Min Act: -0.0000

Data Index: 394812 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6176. Min Act: -0.0000

Data Index: 867891 (The Pile)

Max Activating Token Index: 40

Text #16

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1445172 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6372. Min Act: -0.0000

Data Index: 440816 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1447078 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 1.1009. Min Range: -1.1009

Max Act: 0.5909. Min Act: -0.0000

Data Index: 555499 (The Pile)

Max Activating Token Index: 889