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

Dataset: The Pile

Neuron 1443 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1754780 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.9629. Min Act: -0.0000

Data Index: 479468 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1117807 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.8304. Min Act: -0.0000

Data Index: 682898 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7789. Min Act: -0.0000

Data Index: 687807 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1332195 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7911. Min Act: -0.0000

Data Index: 265655 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1033310 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1103362 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1805428 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6154. Min Act: -0.0000

Data Index: 75603 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7559. Min Act: -0.0000

Data Index: 655044 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1573692 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1561206 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6865. Min Act: -0.0000

Data Index: 377514 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7246. Min Act: -0.0000

Data Index: 385503 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6842. Min Act: -0.0000

Data Index: 514276 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6575. Min Act: -0.0000

Data Index: 35085 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1016909 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1738293 (The Pile)

Max Activating Token Index: 525