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

Dataset: The Pile

Neuron 835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8004. Min Act: -0.0000

Data Index: 3446 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8653. Min Act: -0.0000

Data Index: 647957 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1557818 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1833733 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1581821 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1030169 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1789075 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7923. Min Act: -0.0000

Data Index: 561395 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7455. Min Act: -0.0000

Data Index: 480590 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8724. Min Act: -0.0000

Data Index: 976039 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1950130 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6770. Min Act: -0.0000

Data Index: 143191 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6968. Min Act: -0.0000

Data Index: 674412 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1889056 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1213694 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6498. Min Act: -0.0000

Data Index: 20590 (The Pile)

Max Activating Token Index: 662

Text #16

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6275. Min Act: -0.0000

Data Index: 330701 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7879. Min Act: -0.0000

Data Index: 265056 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1639640 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1720635 (The Pile)

Max Activating Token Index: 984