Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 648 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0868. Min Act: -0.0002

Data Index: 780731 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1301012 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0860. Min Act: -0.0002

Data Index: 730077 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0873. Min Act: -0.0002

Data Index: 356964 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0841. Min Act: -0.0002

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0850. Min Act: -0.0002

Data Index: 492677 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0002

Data Index: 850218 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0857. Min Act: -0.0002

Data Index: 196677 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0827. Min Act: -0.0002

Data Index: 243225 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0833. Min Act: -0.0002

Data Index: 371324 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1043286 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0812. Min Act: -0.0002

Data Index: 297313 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0756. Min Act: -0.0002

Data Index: 420334 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0801. Min Act: -0.0002

Data Index: 860648 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0811. Min Act: -0.0002

Data Index: 524792 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0804. Min Act: -0.0002

Data Index: 154513 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0794. Min Act: -0.0002

Data Index: 662246 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0822. Min Act: -0.0002

Data Index: 633509 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0779. Min Act: -0.0002

Data Index: 161682 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0746. Min Act: -0.0002

Data Index: 968715 (C4 (Web Text))

Max Activating Token Index: 1014