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

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

Neuron 4507 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.9047. Min Act: -0.0000

Data Index: 467847 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.5068. Min Act: -0.0000

Data Index: 321708 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.4075. Min Act: -0.0000

Data Index: 94170 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3925. Min Act: -0.0000

Data Index: 1176099 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.4595. Min Act: -0.0000

Data Index: 467578 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3683. Min Act: -0.0000

Data Index: 363721 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1322330 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.3294. Min Act: -0.0000

Data Index: 1285197 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2933. Min Act: -0.0000

Data Index: 464338 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1122602 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2755. Min Act: -0.0000

Data Index: 801895 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2613. Min Act: -0.0000

Data Index: 300001 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1288250 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.1590. Min Act: -0.0000

Data Index: 573627 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2188. Min Act: -0.0000

Data Index: 933796 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2150. Min Act: -0.0000

Data Index: 1347027 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2048. Min Act: -0.0000

Data Index: 810963 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2298. Min Act: -0.0000

Data Index: 388222 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.0733. Min Act: -0.0000

Data Index: 22334 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.9047. Min Range: -1.9047

Max Act: 1.2064. Min Act: -0.0000

Data Index: 300874 (C4 (Web Text))

Max Activating Token Index: 906