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

Dataset: The Pile

Neuron 3715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.8729. Min Act: -0.0000

Data Index: 57349 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1209790 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7961. Min Act: -0.0000

Data Index: 396043 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7398. Min Act: -0.0000

Data Index: 963683 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1059393 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1007823 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1815805 (The Pile)

Max Activating Token Index: 699

Text #7

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1755176 (The Pile)

Max Activating Token Index: 709

Text #8

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1449010 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.7363. Min Act: -0.0000

Data Index: 31878 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6965. Min Act: -0.0000

Data Index: 876842 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1199823 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1187750 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6625. Min Act: -0.0000

Data Index: 887251 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6660. Min Act: -0.0000

Data Index: 468829 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1567377 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1216720 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.5937. Min Act: -0.0000

Data Index: 403721 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6513. Min Act: -0.0000

Data Index: 412499 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 0.8729. Min Range: -0.8729

Max Act: 0.6433. Min Act: -0.0000

Data Index: 759545 (The Pile)

Max Activating Token Index: 593