Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2975 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0003

Data Index: 29171 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1428951 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0901. Min Act: -0.0003

Data Index: 1070406 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0889. Min Act: -0.0003

Data Index: 1358813 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0872. Min Act: -0.0003

Data Index: 67048 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0830. Min Act: -0.0003

Data Index: 779100 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1460568 (Python Code)

Max Activating Token Index: 645

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0830. Min Act: -0.0003

Data Index: 1519924 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1409977 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0833. Min Act: -0.0003

Data Index: 1443973 (Python Code)

Max Activating Token Index: 742

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1439803 (Python Code)

Max Activating Token Index: 578

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0849. Min Act: -0.0003

Data Index: 8397 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1534258 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0824. Min Act: -0.0003

Data Index: 500915 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0875. Min Act: -0.0003

Data Index: 1654300 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1512855 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1547097 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0816. Min Act: -0.0003

Data Index: 982094 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0841. Min Act: -0.0003

Data Index: 1074633 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0840. Min Act: -0.0003

Data Index: 503509 (C4 (Web Text))

Max Activating Token Index: 8