Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1306432 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1313566 (The Pile)

Max Activating Token Index: 357

Text #2

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9868. Min Act: -0.0000

Data Index: 582189 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1728482 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0410. Min Act: -0.0000

Data Index: 486121 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1818220 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1769800 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.1939. Min Act: -0.0000

Data Index: 733007 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0371. Min Act: -0.0000

Data Index: 173019 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0776. Min Act: -0.0000

Data Index: 862580 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1697284 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1661476 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1217718 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1586948 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1709307 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9908. Min Act: -0.0000

Data Index: 317349 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1061299 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1742290 (The Pile)

Max Activating Token Index: 584

Text #18

Max Range: 1.3782. Min Range: -1.3782

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1208447 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 1.3782. Min Range: -1.3782

Max Act: 1.0863. Min Act: -0.0000

Data Index: 600699 (The Pile)

Max Activating Token Index: 980