Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 569 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2331. Min Act: -0.0001

Data Index: 976063 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1056296 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1192616 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1935. Min Act: -0.0001

Data Index: 87638 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1867. Min Act: -0.0001

Data Index: 152620 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1868. Min Act: -0.0001

Data Index: 162356 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1961. Min Act: -0.0001

Data Index: 363703 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1805. Min Act: -0.0001

Data Index: 872273 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1755. Min Act: -0.0001

Data Index: 287873 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1900. Min Act: -0.0001

Data Index: 158142 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1876. Min Act: -0.0001

Data Index: 870890 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1340337 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1819. Min Act: -0.0001

Data Index: 240094 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1865. Min Act: -0.0001

Data Index: 94647 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1089516 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1791. Min Act: -0.0001

Data Index: 857465 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1887. Min Act: -0.0001

Data Index: 659388 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1748. Min Act: -0.0001

Data Index: 704406 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1719. Min Act: -0.0001

Data Index: 400312 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1653. Min Act: -0.0001

Data Index: 933895 (C4 (Web Text))

Max Activating Token Index: 153