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

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

Neuron 5596 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: 2.8792. Min Range: -2.8792

Max Act: 2.8792. Min Act: -0.0000

Data Index: 218258 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.4620. Min Act: -0.0000

Data Index: 1347178 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2580. Min Act: -0.0000

Data Index: 381657 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.3567. Min Act: -0.0000

Data Index: 728255 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2165. Min Act: -0.0000

Data Index: 789704 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.3312. Min Act: -0.0000

Data Index: 604890 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2966. Min Act: -0.0000

Data Index: 671124 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2780. Min Act: -0.0000

Data Index: 435668 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1664. Min Act: -0.0000

Data Index: 260798 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2690. Min Act: -0.0000

Data Index: 972901 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2632. Min Act: -0.0000

Data Index: 1057194 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2513. Min Act: -0.0000

Data Index: 682024 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1398. Min Act: -0.0000

Data Index: 63516 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2125. Min Act: -0.0000

Data Index: 26255 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.2022. Min Act: -0.0000

Data Index: 259713 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1965. Min Act: -0.0000

Data Index: 519516 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.0779. Min Act: -0.0000

Data Index: 1318973 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1928. Min Act: -0.0000

Data Index: 513474 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1819. Min Act: -0.0000

Data Index: 1183189 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 2.8792. Min Range: -2.8792

Max Act: 2.1702. Min Act: -0.0000

Data Index: 1278429 (C4 (Web Text))

Max Activating Token Index: 920