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

Dataset: The Pile

Neuron 1215 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.9768. Min Act: -0.0000

Data Index: 336197 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7763. Min Act: -0.0000

Data Index: 731614 (The Pile)

Max Activating Token Index: 84

Text #2

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8395. Min Act: -0.0000

Data Index: 833860 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.8809. Min Act: -0.0000

Data Index: 968393 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.7633. Min Act: -0.0000

Data Index: 771012 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1098398 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1680435 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1092937 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.6904. Min Act: -0.0000

Data Index: 727752 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1097364 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.4361. Min Act: -0.0000

Data Index: 446676 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1428196 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.4306. Min Act: -0.0000

Data Index: 999734 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.4740. Min Act: -0.0000

Data Index: 408435 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1785112 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1577409 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1528859 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1050367 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.4997. Min Act: -0.0000

Data Index: 689391 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 0.9768. Min Range: -0.9768

Max Act: 0.4195. Min Act: -0.0000

Data Index: 342586 (The Pile)

Max Activating Token Index: 435