Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1455 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.9182. Min Act: -0.0000

Data Index: 667859 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.8330. Min Act: -0.0000

Data Index: 53178 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.7606. Min Act: -0.0000

Data Index: 906773 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.6312. Min Act: -0.0000

Data Index: 340038 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.7125. Min Act: -0.0000

Data Index: 394495 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.6756. Min Act: -0.0000

Data Index: 712702 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1205742 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.6959. Min Act: -0.0000

Data Index: 677721 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1192143 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5939. Min Act: -0.0000

Data Index: 484308 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5472. Min Act: -0.0000

Data Index: 914441 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5755. Min Act: -0.0000

Data Index: 135522 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5752. Min Act: -0.0000

Data Index: 871177 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5631. Min Act: -0.0000

Data Index: 973530 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5797. Min Act: -0.0000

Data Index: 178770 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5592. Min Act: -0.0000

Data Index: 710324 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5071. Min Act: -0.0000

Data Index: 319529 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5292. Min Act: -0.0000

Data Index: 789621 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5413. Min Act: -0.0000

Data Index: 606945 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.9182. Min Range: -0.9182

Max Act: 0.5561. Min Act: -0.0000

Data Index: 475707 (C4 (Web Text))

Max Activating Token Index: 858