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

Dataset: The Pile

Neuron 3527 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: 1.1933. Min Range: -1.1933

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1430603 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1835. Min Act: -0.0000

Data Index: 766826 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1286. Min Act: -0.0000

Data Index: 1419114 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1248636 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0804. Min Act: -0.0000

Data Index: 222436 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1230650 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0409. Min Act: -0.0000

Data Index: 782675 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0679. Min Act: -0.0000

Data Index: 232998 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0307. Min Act: -0.0000

Data Index: 58540 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0537. Min Act: -0.0000

Data Index: 897645 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9607. Min Act: -0.0000

Data Index: 136575 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1595857 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0178. Min Act: -0.0000

Data Index: 97026 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1516111 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1346927 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1075146 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1928643 (The Pile)

Max Activating Token Index: 633

Text #17

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1501589 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 1.1933. Min Range: -1.1933

Max Act: 0.9788. Min Act: -0.0000

Data Index: 671922 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 1.1933. Min Range: -1.1933

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1331926 (The Pile)

Max Activating Token Index: 599