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

Dataset: The Pile

Neuron 1998 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: 1.3579. Min Range: -1.3579

Max Act: 1.1522. Min Act: -0.0000

Data Index: 1446490 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1963284 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1269173 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1384698 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1542636 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0659. Min Act: -0.0000

Data Index: 577328 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.2289. Min Act: -0.0000

Data Index: 177379 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1201052 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1820523 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1835006 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1473752 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0121. Min Act: -0.0000

Data Index: 35521 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0717. Min Act: -0.0000

Data Index: 973295 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.1196. Min Act: -0.0000

Data Index: 993326 (The Pile)

Max Activating Token Index: 535

Text #14

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0919. Min Act: -0.0000

Data Index: 284736 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 1.3579. Min Range: -1.3579

Max Act: 0.9624. Min Act: -0.0000

Data Index: 847526 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1079503 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0515. Min Act: -0.0000

Data Index: 245596 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1295647 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 1.3579. Min Range: -1.3579

Max Act: 1.0001. Min Act: -0.0000

Data Index: 638589 (The Pile)

Max Activating Token Index: 483