Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1330 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2354. Min Act: -0.0005

Data Index: 1181626 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2160. Min Act: -0.0005

Data Index: 946689 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2121. Min Act: -0.0005

Data Index: 1283507 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1984. Min Act: -0.0005

Data Index: 333689 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2038. Min Act: -0.0005

Data Index: 979361 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2000. Min Act: -0.0005

Data Index: 1182015 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2063. Min Act: -0.0005

Data Index: 139553 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1988. Min Act: -0.0005

Data Index: 869818 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1890. Min Act: -0.0005

Data Index: 583092 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.2009. Min Act: -0.0005

Data Index: 1150981 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1917. Min Act: -0.0005

Data Index: 1020771 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1977. Min Act: -0.0005

Data Index: 212812 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1828. Min Act: -0.0005

Data Index: 561103 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1958. Min Act: -0.0005

Data Index: 257684 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1887. Min Act: -0.0005

Data Index: 1062698 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1867. Min Act: -0.0005

Data Index: 1178284 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1770. Min Act: -0.0005

Data Index: 1253903 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1887. Min Act: -0.0005

Data Index: 284870 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1772. Min Act: -0.0005

Data Index: 1217168 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.2354. Min Range: -0.2354

Max Act: 0.1745. Min Act: -0.0005

Data Index: 263339 (C4 (Web Text))

Max Activating Token Index: 697