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

Dataset: The Pile

Neuron 1191 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0971. Min Range: -1.0971

Max Act: 1.0971. Min Act: -0.0000

Data Index: 376225 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 1.0971. Min Range: -1.0971

Max Act: 1.0268. Min Act: -0.0000

Data Index: 457464 (The Pile)

Max Activating Token Index: 525

Text #2

Max Range: 1.0971. Min Range: -1.0971

Max Act: 1.0404. Min Act: -0.0000

Data Index: 1609878 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 1.0971. Min Range: -1.0971

Max Act: 1.0728. Min Act: -0.0000

Data Index: 42451 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9638. Min Act: -0.0000

Data Index: 24660 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1107256 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1886653 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1196663 (The Pile)

Max Activating Token Index: 491

Text #8

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1374159 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1116698 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1150348 (The Pile)

Max Activating Token Index: 454

Text #11

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1589226 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9620. Min Act: -0.0000

Data Index: 558740 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9731. Min Act: -0.0000

Data Index: 362967 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1678942 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9330. Min Act: -0.0000

Data Index: 704954 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9026. Min Act: -0.0000

Data Index: 836283 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1252734 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.9219. Min Act: -0.0000

Data Index: 456819 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 1.0971. Min Range: -1.0971

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1213540 (The Pile)

Max Activating Token Index: 917