Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 624 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1254. Min Act: -0.0002

Data Index: 200113 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1102. Min Act: -0.0002

Data Index: 854629 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1042. Min Act: -0.0002

Data Index: 481046 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1014. Min Act: -0.0002

Data Index: 149034 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1040. Min Act: -0.0002

Data Index: 659840 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1037. Min Act: -0.0002

Data Index: 891779 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1063. Min Act: -0.0002

Data Index: 650197 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.1016. Min Act: -0.0002

Data Index: 563571 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0988. Min Act: -0.0002

Data Index: 749121 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1120829 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0948. Min Act: -0.0002

Data Index: 104793 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1165131 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1282029 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0947. Min Act: -0.0002

Data Index: 579511 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0901. Min Act: -0.0002

Data Index: 10600 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0888. Min Act: -0.0001

Data Index: 317993 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0911. Min Act: -0.0002

Data Index: 497706 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0880. Min Act: -0.0002

Data Index: 667427 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0888. Min Act: -0.0002

Data Index: 32798 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1254. Min Range: -0.1254

Max Act: 0.0877. Min Act: -0.0002

Data Index: 478478 (C4 (Web Text))

Max Activating Token Index: 133