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

Dataset: The Pile

Neuron 1723 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1984139 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1521174 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8029. Min Act: -0.0000

Data Index: 756848 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.8014. Min Act: -0.0000

Data Index: 405150 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7695. Min Act: -0.0000

Data Index: 3686 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1470637 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6988. Min Act: -0.0000

Data Index: 319413 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1396980 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1084836 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5879. Min Act: -0.0000

Data Index: 402271 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5712. Min Act: -0.0000

Data Index: 293670 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6323. Min Act: -0.0000

Data Index: 780397 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5875. Min Act: -0.0000

Data Index: 34402 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1476102 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6446. Min Act: -0.0000

Data Index: 965090 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5781. Min Act: -0.0000

Data Index: 142211 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.5928. Min Act: -0.0000

Data Index: 768949 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6222. Min Act: -0.0000

Data Index: 533621 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1601939 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.9697. Min Range: -0.9697

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1424649 (The Pile)

Max Activating Token Index: 584