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

Dataset: The Pile

Neuron 576 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: 1.2984. Min Range: -1.2984

Max Act: 1.2984. Min Act: -0.0000

Data Index: 488882 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2925. Min Act: -0.0000

Data Index: 326843 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1551. Min Act: -0.0000

Data Index: 1460778 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1850. Min Act: -0.0000

Data Index: 816897 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1813324 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.1670. Min Act: -0.0000

Data Index: 821965 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0826. Min Act: -0.0000

Data Index: 930611 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1913868 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1258238 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1047061 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1371827 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9854. Min Act: -0.0000

Data Index: 576659 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 1.2984. Min Range: -1.2984

Max Act: 1.0366. Min Act: 0.0000

Data Index: 1618175 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9418. Min Act: -0.0000

Data Index: 110206 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9651. Min Act: -0.0000

Data Index: 41962 (The Pile)

Max Activating Token Index: 37

Text #15

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1435927 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1639822 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.8765. Min Act: -0.0000

Data Index: 780171 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1241531 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 1.2984. Min Range: -1.2984

Max Act: 0.8974. Min Act: 0.0000

Data Index: 909847 (The Pile)

Max Activating Token Index: 23