Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2245. Min Act: -0.0002

Data Index: 1247673 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2110. Min Act: -0.0002

Data Index: 23686 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2025. Min Act: -0.0002

Data Index: 243310 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2130. Min Act: -0.0002

Data Index: 1177176 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1913. Min Act: -0.0002

Data Index: 350173 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1890. Min Act: -0.0002

Data Index: 707078 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1996. Min Act: -0.0003

Data Index: 1074950 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1837. Min Act: -0.0003

Data Index: 731205 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1979. Min Act: -0.0003

Data Index: 1078999 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1910. Min Act: -0.0003

Data Index: 748876 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1862. Min Act: -0.0002

Data Index: 1172200 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1948. Min Act: -0.0003

Data Index: 947096 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1883. Min Act: -0.0003

Data Index: 926305 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1876. Min Act: -0.0002

Data Index: 864392 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1802. Min Act: -0.0003

Data Index: 258207 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1774. Min Act: -0.0003

Data Index: 469335 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1802. Min Act: -0.0002

Data Index: 366 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1707. Min Act: -0.0003

Data Index: 1033789 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1754. Min Act: -0.0002

Data Index: 933614 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1827. Min Act: -0.0003

Data Index: 388877 (C4 (Web Text))

Max Activating Token Index: 104