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

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

Neuron 3378 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2701. Min Act: -0.0000

Data Index: 743307 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2819. Min Act: -0.0000

Data Index: 933147 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1292440 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2295. Min Act: -0.0000

Data Index: 765891 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2317. Min Act: -0.0000

Data Index: 712483 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1100859 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2269. Min Act: -0.0000

Data Index: 181656 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1342790 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2074. Min Act: -0.0000

Data Index: 309974 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1155307 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1995. Min Act: -0.0000

Data Index: 746058 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2035. Min Act: -0.0000

Data Index: 867511 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2030. Min Act: -0.0000

Data Index: 590212 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1971. Min Act: -0.0000

Data Index: 810537 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1942. Min Act: -0.0000

Data Index: 217086 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2093. Min Act: -0.0000

Data Index: 150165 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1788. Min Act: -0.0000

Data Index: 145071 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1969. Min Act: -0.0000

Data Index: 838583 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1832. Min Act: -0.0001

Data Index: 1263610 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2055. Min Act: -0.0000

Data Index: 590373 (C4 (Web Text))

Max Activating Token Index: 886