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

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

Neuron 4778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0781. Min Act: -0.0002

Data Index: 547398 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0758. Min Act: -0.0002

Data Index: 10990 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0780. Min Act: -0.0002

Data Index: 295428 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0754. Min Act: -0.0002

Data Index: 402734 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1130132 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0742. Min Act: -0.0002

Data Index: 181158 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1026303 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0762. Min Act: -0.0002

Data Index: 926377 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0762. Min Act: -0.0002

Data Index: 277692 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0793. Min Act: -0.0002

Data Index: 113807 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1134797 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0706. Min Act: -0.0002

Data Index: 28938 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0734. Min Act: -0.0002

Data Index: 617641 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0683. Min Act: -0.0002

Data Index: 388889 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0743. Min Act: -0.0002

Data Index: 708272 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1250656 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0716. Min Act: -0.0002

Data Index: 927942 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0679. Min Act: -0.0002

Data Index: 853079 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0710. Min Act: -0.0002

Data Index: 794830 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0683. Min Act: -0.0002

Data Index: 999084 (C4 (Web Text))

Max Activating Token Index: 745