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

Dataset: The Pile

Neuron 2614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1062027 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.6196. Min Act: -0.0000

Data Index: 936005 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.6553. Min Act: -0.0000

Data Index: 434502 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.9376. Min Act: -0.0000

Data Index: 497593 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1165674 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1758096 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0363. Min Act: -0.0000

Data Index: 254032 (The Pile)

Max Activating Token Index: 929

Text #7

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1602437 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0893. Min Act: -0.0000

Data Index: 28593 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0809. Min Act: -0.0000

Data Index: 270667 (The Pile)

Max Activating Token Index: 983

Text #10

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0571. Min Act: -0.0000

Data Index: 148563 (The Pile)

Max Activating Token Index: 773

Text #11

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.9776. Min Act: -0.0000

Data Index: 477641 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1497079 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.8026. Min Act: -0.0000

Data Index: 106709 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0145. Min Act: -0.0001

Data Index: 1524906 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.8625. Min Act: -0.0000

Data Index: 115983 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1817230 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.8142. Min Act: -0.0000

Data Index: 852320 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1788457 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 1.6937. Min Range: -1.6937

Max Act: 0.7888. Min Act: -0.0000

Data Index: 261418 (The Pile)

Max Activating Token Index: 51