Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1079684 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1093502 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1082. Min Act: -0.0000

Data Index: 663242 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1055. Min Act: -0.0000

Data Index: 464317 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1038. Min Act: -0.0000

Data Index: 769817 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1107. Min Act: -0.0000

Data Index: 248426 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1230409 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0821. Min Act: -0.0000

Data Index: 680829 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0792. Min Act: -0.0000

Data Index: 258128 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0870. Min Act: -0.0000

Data Index: 853357 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1032614 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0798. Min Act: -0.0000

Data Index: 685551 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0827. Min Act: -0.0000

Data Index: 708172 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0823. Min Act: -0.0000

Data Index: 54306 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0871. Min Act: -0.0000

Data Index: 708413 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1054075 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0753. Min Act: -0.0000

Data Index: 341200 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0740. Min Act: -0.0000

Data Index: 210498 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0685. Min Act: -0.0000

Data Index: 18287 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1023155 (C4 (Web Text))

Max Activating Token Index: 838