Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4142 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.7746. Min Act: -0.0000

Data Index: 1105592 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.4604. Min Act: -0.0000

Data Index: 799298 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.2551. Min Act: -0.0000

Data Index: 490106 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.1404. Min Act: -0.0000

Data Index: 87182 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1221045 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.0416. Min Act: -0.0000

Data Index: 968967 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9885. Min Act: -0.0000

Data Index: 89067 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1220268 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9333. Min Act: -0.0000

Data Index: 741212 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9158. Min Act: -0.0000

Data Index: 79351 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9075. Min Act: -0.0000

Data Index: 410747 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9376. Min Act: -0.0000

Data Index: 634348 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1152748 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1159927 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.8434. Min Act: -0.0000

Data Index: 647799 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.9776. Min Act: -0.0000

Data Index: 70478 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.8673. Min Act: -0.0000

Data Index: 714686 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1040050 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.7937. Min Act: -0.0000

Data Index: 868187 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 1.7746. Min Range: -1.7746

Max Act: 0.8473. Min Act: -0.0000

Data Index: 458163 (C4 (Web Text))

Max Activating Token Index: 792