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

Dataset: The Pile

Neuron 475 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: 1.4242. Min Range: -1.4242

Max Act: 1.3776. Min Act: -0.0000

Data Index: 39515 (The Pile)

Max Activating Token Index: 970

Text #1

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.4242. Min Act: -0.0000

Data Index: 487473 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.3860. Min Act: -0.0000

Data Index: 1678579 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2933. Min Act: -0.0000

Data Index: 382746 (The Pile)

Max Activating Token Index: 470

Text #4

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1735447 (The Pile)

Max Activating Token Index: 856

Text #5

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.3698. Min Act: -0.0000

Data Index: 1941840 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2422. Min Act: -0.0000

Data Index: 494527 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1035058 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1843. Min Act: -0.0000

Data Index: 924901 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1767911 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1301224 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1432095 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1946207 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0797. Min Act: -0.0000

Data Index: 676551 (The Pile)

Max Activating Token Index: 997

Text #14

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.1649. Min Act: -0.0000

Data Index: 283383 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.2923. Min Act: -0.0000

Data Index: 162808 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.3966. Min Act: -0.0000

Data Index: 715112 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0211. Min Act: -0.0001

Data Index: 435421 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0666. Min Act: -0.0000

Data Index: 913782 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 1.4242. Min Range: -1.4242

Max Act: 1.0030. Min Act: -0.0000

Data Index: 677490 (The Pile)

Max Activating Token Index: 993