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

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

Neuron 94 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: 0.1029. Min Range: -0.1029

Max Act: 0.1029. Min Act: -0.0000

Data Index: 745112 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0940. Min Act: -0.0000

Data Index: 418522 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0977. Min Act: -0.0000

Data Index: 606845 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1275140 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0909. Min Act: -0.0000

Data Index: 675414 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0857. Min Act: -0.0000

Data Index: 126513 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0920. Min Act: -0.0000

Data Index: 329497 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1398210 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0914. Min Act: -0.0000

Data Index: 420326 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0708. Min Act: -0.0000

Data Index: 50869 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0773. Min Act: -0.0000

Data Index: 782349 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0763. Min Act: -0.0000

Data Index: 229609 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0736. Min Act: -0.0000

Data Index: 515270 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0801. Min Act: -0.0000

Data Index: 112951 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1093474 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0792. Min Act: -0.0000

Data Index: 785247 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0825. Min Act: -0.0000

Data Index: 89926 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0766. Min Act: -0.0000

Data Index: 686481 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0708. Min Act: -0.0000

Data Index: 238005 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1268844 (C4 (Web Text))

Max Activating Token Index: 621