Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 606 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1221431 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.7063. Min Act: -0.0000

Data Index: 578535 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.6208. Min Act: -0.0000

Data Index: 831809 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.6194. Min Act: -0.0000

Data Index: 417422 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1001536 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5698. Min Act: -0.0000

Data Index: 529297 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5592. Min Act: -0.0000

Data Index: 743440 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5626. Min Act: -0.0000

Data Index: 534144 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5709. Min Act: -0.0000

Data Index: 966415 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1301205 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5667. Min Act: -0.0000

Data Index: 816895 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1237862 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1352724 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5002. Min Act: -0.0000

Data Index: 735134 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5062. Min Act: -0.0000

Data Index: 529558 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1109321 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1226543 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1112039 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5058. Min Act: -0.0000

Data Index: 910330 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4842. Min Act: -0.0000

Data Index: 725748 (C4 (Web Text))

Max Activating Token Index: 222