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

Dataset: The Pile

Neuron 1493 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: 0.8742. Min Range: -0.8742

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1977568 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8290. Min Act: -0.0000

Data Index: 48726 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8284. Min Act: -0.0000

Data Index: 915637 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8240. Min Act: -0.0000

Data Index: 36776 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8135. Min Act: -0.0000

Data Index: 645402 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1567823 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1658640 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1269448 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7655. Min Act: -0.0000

Data Index: 271816 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1362536 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1905926 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8166. Min Act: -0.0000

Data Index: 629426 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1777485 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7664. Min Act: -0.0000

Data Index: 236911 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7772. Min Act: -0.0000

Data Index: 444949 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1521789 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7524. Min Act: -0.0000

Data Index: 748706 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1928091 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1775733 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7424. Min Act: -0.0000

Data Index: 299127 (The Pile)

Max Activating Token Index: 564