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

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

Neuron 5474 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8811. Min Range: -3.8811

Max Act: 3.8811. Min Act: -0.0000

Data Index: 1368673 (Python Code)

Max Activating Token Index: 372

Text #1

Max Range: 3.8811. Min Range: -3.8811

Max Act: 3.1573. Min Act: -0.0000

Data Index: 1526647 (Python Code)

Max Activating Token Index: 870

Text #2

Max Range: 3.8811. Min Range: -3.8811

Max Act: 3.1054. Min Act: -0.0000

Data Index: 1489786 (Python Code)

Max Activating Token Index: 398

Text #3

Max Range: 3.8811. Min Range: -3.8811

Max Act: 3.0765. Min Act: -0.0000

Data Index: 1496926 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 3.8811. Min Range: -3.8811

Max Act: 3.0676. Min Act: -0.0000

Data Index: 1450751 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 3.8811. Min Range: -3.8811

Max Act: 3.1647. Min Act: -0.0000

Data Index: 1587520 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.8800. Min Act: -0.0000

Data Index: 1545064 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.8560. Min Act: -0.0000

Data Index: 1633306 (Python Code)

Max Activating Token Index: 593

Text #8

Max Range: 3.8811. Min Range: -3.8811

Max Act: 3.0432. Min Act: -0.0000

Data Index: 1412542 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.7608. Min Act: -0.0000

Data Index: 1639484 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.8214. Min Act: -0.0000

Data Index: 1514356 (Python Code)

Max Activating Token Index: 755

Text #11

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.7915. Min Act: -0.0000

Data Index: 1550552 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.7720. Min Act: 0.0000

Data Index: 1534792 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.6095. Min Act: -0.0000

Data Index: 1455483 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.6729. Min Act: -0.0000

Data Index: 1513940 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.5408. Min Act: -0.0000

Data Index: 1608634 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.5326. Min Act: -0.0000

Data Index: 1461160 (Python Code)

Max Activating Token Index: 842

Text #17

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.6628. Min Act: -0.0000

Data Index: 1495192 (Python Code)

Max Activating Token Index: 750

Text #18

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.8084. Min Act: -0.0000

Data Index: 1425411 (Python Code)

Max Activating Token Index: 909

Text #19

Max Range: 3.8811. Min Range: -3.8811

Max Act: 2.6439. Min Act: -0.0000

Data Index: 1523339 (Python Code)

Max Activating Token Index: 733