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

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

Neuron 4428 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: 0.9780. Min Range: -0.9780

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1638111 (Python Code)

Max Activating Token Index: 940

Text #1

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1544300 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1555673 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1566247 (Python Code)

Max Activating Token Index: 493

Text #4

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1589902 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1620422 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1432031 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1529389 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1643393 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1414528 (Python Code)

Max Activating Token Index: 656

Text #10

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1362768 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1426540 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1611727 (Python Code)

Max Activating Token Index: 650

Text #13

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1503408 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1644272 (Python Code)

Max Activating Token Index: 995

Text #15

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5883. Min Act: -0.0000

Data Index: 73006 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1461239 (Python Code)

Max Activating Token Index: 907

Text #17

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1405257 (Python Code)

Max Activating Token Index: 396

Text #18

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.6065. Min Act: -0.0000

Data Index: 343755 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.9780. Min Range: -0.9780

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1424743 (Python Code)

Max Activating Token Index: 102