Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3581 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2561. Min Act: -0.0002

Data Index: 213650 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2304. Min Act: -0.0003

Data Index: 407794 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2214. Min Act: -0.0003

Data Index: 101558 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2123. Min Act: -0.0002

Data Index: 797652 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2009. Min Act: -0.0003

Data Index: 332528 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1992. Min Act: -0.0002

Data Index: 1017136 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1982. Min Act: -0.0003

Data Index: 111564 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1955. Min Act: -0.0003

Data Index: 1174152 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1926. Min Act: -0.0003

Data Index: 256659 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1918. Min Act: -0.0002

Data Index: 1274673 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1879. Min Act: -0.0002

Data Index: 13884 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1875. Min Act: -0.0002

Data Index: 233281 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1811. Min Act: -0.0003

Data Index: 568365 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1872. Min Act: -0.0002

Data Index: 133176 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1867. Min Act: -0.0002

Data Index: 878797 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1861. Min Act: -0.0002

Data Index: 88664 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1785. Min Act: -0.0002

Data Index: 635042 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1843. Min Act: -0.0002

Data Index: 652144 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1773. Min Act: -0.0002

Data Index: 1111162 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.1820. Min Act: -0.0002

Data Index: 109801 (C4 (Web Text))

Max Activating Token Index: 610