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

Dataset: The Pile

Neuron 5106 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: 1.8815. Min Range: -1.8815

Max Act: 1.8815. Min Act: -0.0000

Data Index: 91166 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1976457 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1669660 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.1844. Min Act: -0.0000

Data Index: 246632 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9440. Min Act: -0.0000

Data Index: 808555 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.1403. Min Act: -0.0000

Data Index: 469768 (The Pile)

Max Activating Token Index: 808

Text #6

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1271873 (The Pile)

Max Activating Token Index: 275

Text #7

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.0802. Min Act: -0.0000

Data Index: 230382 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9465. Min Act: -0.0000

Data Index: 590561 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1412991 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1889329 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9642. Min Act: -0.0000

Data Index: 443422 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.8735. Min Act: -0.0000

Data Index: 72807 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1053152 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9539. Min Act: -0.0000

Data Index: 36048 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.9127. Min Act: -0.0000

Data Index: 160652 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.8019. Min Act: -0.0000

Data Index: 480793 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1134855 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1191570 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 1.8815. Min Range: -1.8815

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1713321 (The Pile)

Max Activating Token Index: 992