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

Dataset: The Pile

Neuron 806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1816364 (The Pile)

Max Activating Token Index: 974

Text #1

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7710. Min Act: -0.0000

Data Index: 60483 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1998302 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7647. Min Act: -0.0000

Data Index: 615252 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7787. Min Act: -0.0000

Data Index: 207057 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1979859 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7391. Min Act: -0.0000

Data Index: 602579 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1560690 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7858. Min Act: -0.0000

Data Index: 705824 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1542231 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7363. Min Act: -0.0000

Data Index: 534771 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7462. Min Act: -0.0000

Data Index: 336058 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7037. Min Act: -0.0000

Data Index: 195572 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1105763 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6118. Min Act: -0.0000

Data Index: 9109 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6943. Min Act: -0.0000

Data Index: 52364 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1050581 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6730. Min Act: -0.0000

Data Index: 247949 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1688366 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 0.9363. Min Range: -0.9363

Max Act: 0.7433. Min Act: -0.0000

Data Index: 539640 (The Pile)

Max Activating Token Index: 981