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

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

Neuron 476 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1058822 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1217. Min Act: -0.0000

Data Index: 568331 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1004. Min Act: -0.0000

Data Index: 610885 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1048. Min Act: -0.0000

Data Index: 430483 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1067150 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0935. Min Act: -0.0000

Data Index: 856882 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1144755 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1352321 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0906. Min Act: -0.0000

Data Index: 15896 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0828. Min Act: -0.0000

Data Index: 674113 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1131839 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1326046 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0797. Min Act: -0.0000

Data Index: 921617 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0753. Min Act: -0.0000

Data Index: 115327 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0834. Min Act: -0.0000

Data Index: 665639 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1236484 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0743. Min Act: -0.0000

Data Index: 143362 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0679. Min Act: -0.0000

Data Index: 290829 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1151138 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1088918 (C4 (Web Text))

Max Activating Token Index: 344