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

Dataset: The Pile

Neuron 355 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: 3.6564. Min Range: -3.6564

Max Act: 3.6564. Min Act: -0.0000

Data Index: 1431087 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.4918. Min Act: -0.0000

Data Index: 169675 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.1624. Min Act: -0.0000

Data Index: 330139 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.1023. Min Act: -0.0000

Data Index: 738550 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.2080. Min Act: -0.0000

Data Index: 245883 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.1723. Min Act: -0.0000

Data Index: 980514 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.1721. Min Act: -0.0000

Data Index: 26502 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.9768. Min Act: -0.0000

Data Index: 954815 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.9420. Min Act: -0.0000

Data Index: 192853 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.0709. Min Act: -0.0000

Data Index: 1426997 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 3.6564. Min Range: -3.6564

Max Act: 3.0829. Min Act: -0.0000

Data Index: 305378 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.8159. Min Act: -0.0000

Data Index: 215179 (The Pile)

Max Activating Token Index: 871

Text #12

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.8722. Min Act: -0.0000

Data Index: 1032303 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.7974. Min Act: -0.0000

Data Index: 1086152 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.8676. Min Act: -0.0000

Data Index: 1508473 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.7119. Min Act: -0.0000

Data Index: 1084446 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.7269. Min Act: -0.0000

Data Index: 280494 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.8544. Min Act: -0.0000

Data Index: 432505 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.7226. Min Act: -0.0000

Data Index: 1061724 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 3.6564. Min Range: -3.6564

Max Act: 2.9715. Min Act: -0.0000

Data Index: 1044969 (The Pile)

Max Activating Token Index: 306