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

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

Neuron 1366 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: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0002

Data Index: 790814 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1081. Min Act: -0.0002

Data Index: 93107 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1002. Min Act: -0.0002

Data Index: 1255753 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1003. Min Act: -0.0002

Data Index: 207041 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0880. Min Act: -0.0002

Data Index: 851997 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1305809 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1035. Min Act: -0.0002

Data Index: 240759 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0936. Min Act: -0.0002

Data Index: 240779 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1390959 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1457904 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0975. Min Act: -0.0002

Data Index: 291804 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0904. Min Act: -0.0002

Data Index: 344940 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0986. Min Act: -0.0002

Data Index: 981779 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1081. Min Act: -0.0002

Data Index: 803638 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0921. Min Act: -0.0002

Data Index: 107635 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0957. Min Act: -0.0002

Data Index: 55918 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1015. Min Act: -0.0002

Data Index: 647236 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1431223 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1244724 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0872. Min Act: -0.0002

Data Index: 450400 (C4 (Web Text))

Max Activating Token Index: 591