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

Dataset: The Pile

Neuron 247 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: 5.0833. Min Range: -5.0833

Max Act: 4.9459. Min Act: -0.0000

Data Index: 447837 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 5.0833. Min Range: -5.0833

Max Act: 5.0833. Min Act: -0.0000

Data Index: 22733 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 5.0833. Min Range: -5.0833

Max Act: 5.0669. Min Act: -0.0000

Data Index: 597050 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6496. Min Act: -0.0000

Data Index: 1373709 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6911. Min Act: -0.0000

Data Index: 51467 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.8244. Min Act: -0.0000

Data Index: 1682456 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6307. Min Act: -0.0000

Data Index: 1469516 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.9895. Min Act: -0.0000

Data Index: 1689773 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.7899. Min Act: -0.0000

Data Index: 1052244 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.7037. Min Act: -0.0000

Data Index: 252762 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6813. Min Act: -0.0000

Data Index: 1910204 (The Pile)

Max Activating Token Index: 830

Text #11

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6661. Min Act: -0.0000

Data Index: 890023 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6948. Min Act: -0.0000

Data Index: 852031 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.8013. Min Act: -0.0000

Data Index: 684212 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.2437. Min Act: -0.0000

Data Index: 1380227 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.5794. Min Act: -0.0000

Data Index: 496446 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6961. Min Act: -0.0000

Data Index: 89090 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.3130. Min Act: -0.0000

Data Index: 1932210 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6714. Min Act: -0.0000

Data Index: 569540 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 5.0833. Min Range: -5.0833

Max Act: 4.6676. Min Act: -0.0000

Data Index: 71959 (The Pile)

Max Activating Token Index: 827