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

Dataset: The Pile

Neuron 5035 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.9443. Min Act: -0.0000

Data Index: 1350170 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.7617. Min Act: -0.0000

Data Index: 89109 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.8480. Min Act: -0.0000

Data Index: 193838 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.8341. Min Act: -0.0000

Data Index: 9326 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.7046. Min Act: -0.0000

Data Index: 954399 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6314. Min Act: -0.0000

Data Index: 899108 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1177265 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.7032. Min Act: -0.0000

Data Index: 979415 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1857255 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1979816 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1063133 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6975. Min Act: -0.0000

Data Index: 916209 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6704. Min Act: -0.0000

Data Index: 884001 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1002703 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1899780 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1327501 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1766984 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6514. Min Act: -0.0000

Data Index: 989906 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1717955 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.9443. Min Range: -0.9443

Max Act: 0.6033. Min Act: -0.0000

Data Index: 318420 (The Pile)

Max Activating Token Index: 863