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

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

Neuron 3098 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8731. Min Act: -0.0001

Data Index: 380817 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.8383. Min Act: -0.0002

Data Index: 1134528 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7532. Min Act: -0.0002

Data Index: 483033 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7638. Min Act: -0.0002

Data Index: 1142051 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7447. Min Act: -0.0002

Data Index: 271529 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.7259. Min Act: -0.0002

Data Index: 806626 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6957. Min Act: -0.0002

Data Index: 590352 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6982. Min Act: -0.0001

Data Index: 238795 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5960. Min Act: -0.0002

Data Index: 1048660 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6759. Min Act: -0.0002

Data Index: 960077 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6675. Min Act: -0.0002

Data Index: 515542 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6611. Min Act: -0.0002

Data Index: 973304 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6746. Min Act: -0.0002

Data Index: 615324 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6532. Min Act: -0.0001

Data Index: 937909 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6516. Min Act: -0.0001

Data Index: 832188 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1064925 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6184. Min Act: -0.0001

Data Index: 743717 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5990. Min Act: -0.0002

Data Index: 786315 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.6260. Min Act: -0.0001

Data Index: 560733 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.8731. Min Range: -0.8731

Max Act: 0.5541. Min Act: -0.0001

Data Index: 513047 (C4 (Web Text))

Max Activating Token Index: 839