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

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

Neuron 4805 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: 0.1035. Min Range: -0.1035

Max Act: 0.1035. Min Act: -0.0002

Data Index: 654225 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.1011. Min Act: -0.0002

Data Index: 854845 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0914. Min Act: -0.0002

Data Index: 496349 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0873. Min Act: -0.0002

Data Index: 980458 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0833. Min Act: -0.0002

Data Index: 539032 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0831. Min Act: -0.0002

Data Index: 104393 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0818. Min Act: -0.0002

Data Index: 417062 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0764. Min Act: -0.0002

Data Index: 713084 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0819. Min Act: -0.0002

Data Index: 957421 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1151570 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1318938 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0754. Min Act: -0.0002

Data Index: 277200 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0786. Min Act: -0.0002

Data Index: 116166 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0768. Min Act: -0.0002

Data Index: 126102 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1270732 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0748. Min Act: -0.0002

Data Index: 901848 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0729. Min Act: -0.0002

Data Index: 32751 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1227457 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0677. Min Act: -0.0002

Data Index: 619676 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0726. Min Act: -0.0002

Data Index: 159367 (C4 (Web Text))

Max Activating Token Index: 547