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

Dataset: The Pile

Neuron 1627 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: 13.5910. Min Range: -13.5910

Max Act: 13.5910. Min Act: -0.0000

Data Index: 1098032 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 13.5910. Min Range: -13.5910

Max Act: 8.5607. Min Act: -0.0000

Data Index: 1746460 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.0341. Min Act: -0.0000

Data Index: 963342 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 13.5910. Min Range: -13.5910

Max Act: 11.3320. Min Act: -0.0000

Data Index: 1036226 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.8595. Min Act: -0.0000

Data Index: 621298 (The Pile)

Max Activating Token Index: 515

Text #5

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1759196 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1728007 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1923534 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.5327. Min Act: -0.0000

Data Index: 183035 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1387281 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6331. Min Act: -0.0000

Data Index: 518699 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1833532 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1229534 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.5889. Min Act: -0.0000

Data Index: 468542 (The Pile)

Max Activating Token Index: 847

Text #14

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1152293 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6479. Min Act: -0.0000

Data Index: 865094 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6245. Min Act: -0.0000

Data Index: 128674 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.5843. Min Act: -0.0000

Data Index: 96757 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1629983 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 13.5910. Min Range: -13.5910

Max Act: 0.6288. Min Act: -0.0000

Data Index: 612220 (The Pile)

Max Activating Token Index: 666