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

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

Neuron 1962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3762. Min Act: -0.0002

Data Index: 533332 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.4358. Min Act: -0.0002

Data Index: 795387 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2733. Min Act: -0.0002

Data Index: 7873 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1970. Min Act: -0.0002

Data Index: 1251700 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2724. Min Act: -0.0002

Data Index: 972058 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1861. Min Act: -0.0002

Data Index: 1198999 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1909. Min Act: -0.0002

Data Index: 20756 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1916. Min Act: -0.0002

Data Index: 1232007 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2814. Min Act: -0.0002

Data Index: 298695 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2267. Min Act: -0.0002

Data Index: 1220370 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.3748. Min Act: -0.0002

Data Index: 279755 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1795. Min Act: -0.0002

Data Index: 119528 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2096. Min Act: -0.0002

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1995. Min Act: -0.0002

Data Index: 795888 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1953. Min Act: -0.0002

Data Index: 897670 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2166. Min Act: -0.0002

Data Index: 334774 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1249. Min Act: -0.0002

Data Index: 697783 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2540. Min Act: -0.0002

Data Index: 269908 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.2494. Min Act: -0.0002

Data Index: 605168 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.4358. Min Range: -1.4358

Max Act: 1.1733. Min Act: -0.0002

Data Index: 281880 (C4 (Web Text))

Max Activating Token Index: 141