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

Dataset: The Pile

Neuron 5075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1603. Min Range: -1.1603

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1353228 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1902029 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.8098. Min Act: -0.0000

Data Index: 328502 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.8847. Min Act: -0.0000

Data Index: 87319 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.8237. Min Act: -0.0000

Data Index: 100622 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1178329 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1872133 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1919747 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7299. Min Act: -0.0000

Data Index: 396669 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7376. Min Act: -0.0000

Data Index: 888893 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7186. Min Act: -0.0000

Data Index: 305785 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1482518 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1956780 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.6969. Min Act: -0.0000

Data Index: 472661 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1546002 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.6605. Min Act: -0.0000

Data Index: 768790 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.6853. Min Act: -0.0000

Data Index: 971325 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1707476 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.7050. Min Act: -0.0000

Data Index: 470140 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 1.1603. Min Range: -1.1603

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1560785 (The Pile)

Max Activating Token Index: 915