Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1269 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.6506. Min Act: -0.0000

Data Index: 107263 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.4935. Min Act: -0.0000

Data Index: 320509 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.5579. Min Act: -0.0000

Data Index: 595515 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.4373. Min Act: -0.0000

Data Index: 904884 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.3817. Min Act: -0.0000

Data Index: 769411 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.2236. Min Act: -0.0000

Data Index: 392859 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1224624 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1065494 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.1936. Min Act: -0.0000

Data Index: 472842 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.2360. Min Act: -0.0000

Data Index: 224912 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.1433. Min Act: -0.0000

Data Index: 351239 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1356828 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.1368. Min Act: -0.0000

Data Index: 356554 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.1072. Min Act: -0.0000

Data Index: 129770 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.1038. Min Act: -0.0000

Data Index: 318748 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.0964. Min Act: -0.0000

Data Index: 367641 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.0951. Min Act: -0.0000

Data Index: 426895 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.0720. Min Act: -0.0000

Data Index: 853143 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.1264. Min Act: -0.0000

Data Index: 820680 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.6506. Min Range: -1.6506

Max Act: 1.0402. Min Act: -0.0000

Data Index: 1130906 (C4 (Web Text))

Max Activating Token Index: 871