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

Dataset: The Pile

Neuron 1366 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.2732. Min Act: -0.0000

Data Index: 82781 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1534. Min Act: -0.0000

Data Index: 215280 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.2739. Min Act: -0.0000

Data Index: 56285 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1599435 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1100. Min Act: -0.0000

Data Index: 834793 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1615357 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1745148 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1227622 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0756. Min Act: -0.0000

Data Index: 672865 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0983. Min Act: -0.0000

Data Index: 743392 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.1218. Min Act: -0.0000

Data Index: 1009472 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1972403 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0655. Min Act: -0.0000

Data Index: 240239 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0673. Min Act: -0.0000

Data Index: 80883 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1827559 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 1.2739. Min Range: -1.2739

Max Act: 0.9790. Min Act: -0.0000

Data Index: 1857692 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0749. Min Act: -0.0000

Data Index: 153939 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0720. Min Act: -0.0000

Data Index: 697193 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1654696 (The Pile)

Max Activating Token Index: 780

Text #19

Max Range: 1.2739. Min Range: -1.2739

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1637479 (The Pile)

Max Activating Token Index: 500