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

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

Neuron 3705 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: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0001

Data Index: 430153 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0995. Min Act: -0.0000

Data Index: 247418 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0909. Min Act: -0.0000

Data Index: 770452 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0895. Min Act: -0.0000

Data Index: 966986 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0870. Min Act: -0.0000

Data Index: 820410 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0865. Min Act: -0.0001

Data Index: 614891 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0829. Min Act: -0.0001

Data Index: 414827 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0786. Min Act: -0.0001

Data Index: 63334 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0798. Min Act: -0.0000

Data Index: 566923 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0794. Min Act: -0.0001

Data Index: 997668 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0771. Min Act: -0.0001

Data Index: 853462 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0823. Min Act: -0.0000

Data Index: 902834 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1074872 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1266139 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1176498 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0747. Min Act: -0.0000

Data Index: 787485 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0738. Min Act: -0.0000

Data Index: 981484 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0740. Min Act: -0.0001

Data Index: 395337 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0703. Min Act: -0.0001

Data Index: 344595 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0779. Min Act: -0.0000

Data Index: 352996 (C4 (Web Text))

Max Activating Token Index: 981