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

Dataset: The Pile

Neuron 4088 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: 0.6666. Min Range: -0.6666

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1803289 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1227571 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1992118 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1898642 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6383. Min Act: -0.0000

Data Index: 510999 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1367447 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1767030 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1698535 (The Pile)

Max Activating Token Index: 805

Text #8

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1703668 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1504499 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1437695 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5673. Min Act: -0.0000

Data Index: 122252 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5372. Min Act: -0.0000

Data Index: 920145 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5429. Min Act: -0.0000

Data Index: 31728 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5357. Min Act: 0.0000

Data Index: 1766707 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1276864 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5491. Min Act: -0.0000

Data Index: 62941 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1365800 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5384. Min Act: -0.0000

Data Index: 192508 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5725. Min Act: -0.0000

Data Index: 95900 (The Pile)

Max Activating Token Index: 616