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

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

Neuron 679 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: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0003

Data Index: 13452 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0806. Min Act: -0.0003

Data Index: 139635 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0752. Min Act: -0.0003

Data Index: 868600 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0832. Min Act: -0.0003

Data Index: 955312 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0736. Min Act: -0.0003

Data Index: 319155 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1239815 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0839. Min Act: -0.0003

Data Index: 994035 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0754. Min Act: -0.0003

Data Index: 195460 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0689. Min Act: -0.0003

Data Index: 413313 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0760. Min Act: -0.0003

Data Index: 877509 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0748. Min Act: -0.0003

Data Index: 162246 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0704. Min Act: -0.0003

Data Index: 1007071 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0754. Min Act: -0.0003

Data Index: 246991 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0787. Min Act: -0.0003

Data Index: 204660 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0689. Min Act: -0.0003

Data Index: 711159 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0700. Min Act: -0.0003

Data Index: 933074 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0705. Min Act: -0.0003

Data Index: 202210 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1141184 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1345070 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0709. Min Act: -0.0003

Data Index: 467380 (C4 (Web Text))

Max Activating Token Index: 679