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

Dataset: The Pile

Neuron 142 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: 1.2822. Min Range: -1.2822

Max Act: 1.2822. Min Act: -0.0000

Data Index: 434947 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1237522 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.2406. Min Act: -0.0000

Data Index: 1332087 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1955. Min Act: -0.0000

Data Index: 286782 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1695067 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.2226. Min Act: -0.0000

Data Index: 678792 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1409062 (The Pile)

Max Activating Token Index: 230

Text #7

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1376553 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1469. Min Act: -0.0000

Data Index: 481179 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1681. Min Act: -0.0000

Data Index: 706400 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1240774 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1366677 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1689. Min Act: -0.0000

Data Index: 297740 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1317. Min Act: -0.0000

Data Index: 1641585 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0927. Min Act: -0.0000

Data Index: 24586 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1636544 (The Pile)

Max Activating Token Index: 479

Text #16

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1899140 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0878. Min Act: -0.0000

Data Index: 416484 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1810300 (The Pile)

Max Activating Token Index: 525

Text #19

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1346. Min Act: -0.0000

Data Index: 304175 (The Pile)

Max Activating Token Index: 918