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

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

Neuron 687 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0905. Min Act: -0.0001

Data Index: 514228 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1626822 (Python Code)

Max Activating Token Index: 952

Text #2

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0827. Min Act: -0.0001

Data Index: 29592 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0807. Min Act: -0.0001

Data Index: 344702 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0828. Min Act: -0.0000

Data Index: 72336 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1500069 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0754. Min Act: -0.0001

Data Index: 627619 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0726. Min Act: -0.0000

Data Index: 482396 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1043475 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0767. Min Act: -0.0000

Data Index: 573292 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0735. Min Act: -0.0000

Data Index: 687356 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0730. Min Act: -0.0001

Data Index: 623401 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0695. Min Act: -0.0000

Data Index: 603895 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1057657 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0698. Min Act: -0.0001

Data Index: 869903 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1454443 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1365208 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0694. Min Act: -0.0000

Data Index: 263242 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0715. Min Act: -0.0000

Data Index: 306079 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0905. Min Range: -0.0905

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1585552 (Python Code)

Max Activating Token Index: 463