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

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

Neuron 1223 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2245. Min Act: -0.0001

Data Index: 934012 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1912. Min Act: -0.0001

Data Index: 358084 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1962. Min Act: -0.0001

Data Index: 50197 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1602843 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1907. Min Act: -0.0001

Data Index: 252203 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1879. Min Act: -0.0001

Data Index: 587701 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1856. Min Act: -0.0001

Data Index: 494446 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1899. Min Act: -0.0001

Data Index: 228120 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1566080 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1910. Min Act: -0.0001

Data Index: 1462437 (Python Code)

Max Activating Token Index: 747

Text #10

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1362973 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1807. Min Act: -0.0001

Data Index: 463238 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1800. Min Act: -0.0001

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1794. Min Act: -0.0001

Data Index: 460083 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1504350 (Python Code)

Max Activating Token Index: 662

Text #15

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1603151 (Python Code)

Max Activating Token Index: 988

Text #16

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1623118 (Python Code)

Max Activating Token Index: 64

Text #17

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1623943 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1504838 (Python Code)

Max Activating Token Index: 737

Text #19

Max Range: 0.2245. Min Range: -0.2245

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1606866 (Python Code)

Max Activating Token Index: 905