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

Dataset: The Pile

Neuron 2995 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.6045. Min Act: 0.0000

Data Index: 833444 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.7655. Min Act: -0.0000

Data Index: 1018894 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.7115. Min Act: -0.0000

Data Index: 1590144 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.5641. Min Act: -0.0000

Data Index: 1062920 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3508. Min Act: -0.0000

Data Index: 1491791 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3838. Min Act: -0.0000

Data Index: 961521 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.1985. Min Act: -0.0000

Data Index: 566124 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3441. Min Act: -0.0000

Data Index: 303657 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3240. Min Act: -0.0000

Data Index: 1347607 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.2526. Min Act: -0.0000

Data Index: 1792495 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.0750. Min Act: -0.0000

Data Index: 730597 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.1457. Min Act: -0.0000

Data Index: 245340 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 3.7655. Min Range: -3.7655

Max Act: 2.9805. Min Act: -0.0000

Data Index: 863043 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.2673. Min Act: -0.0000

Data Index: 1529069 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 3.7655. Min Range: -3.7655

Max Act: 2.7930. Min Act: -0.0000

Data Index: 1345112 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.1155. Min Act: -0.0000

Data Index: 397709 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.0756. Min Act: -0.0000

Data Index: 496659 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.0618. Min Act: -0.0000

Data Index: 317602 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.2032. Min Act: -0.0000

Data Index: 630990 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.1394. Min Act: -0.0000

Data Index: 990468 (The Pile)

Max Activating Token Index: 957