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

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

Neuron 2694 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: 0.9679. Min Range: -0.9679

Max Act: 0.9679. Min Act: -0.0000

Data Index: 976079 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.9484. Min Act: -0.0000

Data Index: 157983 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.9065. Min Act: -0.0000

Data Index: 905870 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8134. Min Act: -0.0000

Data Index: 571235 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1096933 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1134940 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7618. Min Act: -0.0000

Data Index: 379052 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1391825 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7490. Min Act: -0.0000

Data Index: 322030 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7304. Min Act: -0.0000

Data Index: 97091 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7496. Min Act: -0.0000

Data Index: 738571 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7237. Min Act: -0.0000

Data Index: 452243 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1512641 (Python Code)

Max Activating Token Index: 520

Text #13

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1633822 (Python Code)

Max Activating Token Index: 939

Text #14

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1427295 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1644450 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1411159 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6750. Min Act: -0.0000

Data Index: 694809 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6541. Min Act: -0.0000

Data Index: 909024 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6283. Min Act: -0.0000

Data Index: 308190 (C4 (Web Text))

Max Activating Token Index: 73