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

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

Neuron 1397 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: 0.0984. Min Range: -0.0984

Max Act: 0.0984. Min Act: -0.0002

Data Index: 289785 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1223610 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0966. Min Act: -0.0002

Data Index: 877157 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1196935 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0886. Min Act: -0.0002

Data Index: 35405 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0909. Min Act: -0.0002

Data Index: 40054 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0930. Min Act: -0.0002

Data Index: 374575 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0888. Min Act: -0.0002

Data Index: 994580 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1111716 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0890. Min Act: -0.0002

Data Index: 205416 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0910. Min Act: -0.0002

Data Index: 158006 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0871. Min Act: -0.0002

Data Index: 759746 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0831. Min Act: -0.0002

Data Index: 728927 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0833. Min Act: -0.0002

Data Index: 233099 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0851. Min Act: -0.0002

Data Index: 269212 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0883. Min Act: -0.0002

Data Index: 675498 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0849. Min Act: -0.0002

Data Index: 594264 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0881. Min Act: -0.0002

Data Index: 735669 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0810. Min Act: -0.0002

Data Index: 340148 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.0984. Min Range: -0.0984

Max Act: 0.0856. Min Act: -0.0002

Data Index: 936877 (C4 (Web Text))

Max Activating Token Index: 655