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

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

Neuron 1558 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0002

Data Index: 1498234 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1788. Min Act: -0.0002

Data Index: 1444772 (Python Code)

Max Activating Token Index: 587

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1783. Min Act: -0.0002

Data Index: 1621097 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1762. Min Act: -0.0002

Data Index: 1643376 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1717. Min Act: -0.0002

Data Index: 1451112 (Python Code)

Max Activating Token Index: 698

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1729. Min Act: -0.0002

Data Index: 1585042 (Python Code)

Max Activating Token Index: 651

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1701. Min Act: -0.0002

Data Index: 1590413 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1742. Min Act: -0.0002

Data Index: 1633396 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1707. Min Act: -0.0002

Data Index: 1474549 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1671. Min Act: -0.0002

Data Index: 1529955 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1694. Min Act: -0.0002

Data Index: 1585669 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1594. Min Act: -0.0002

Data Index: 1638357 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1618. Min Act: -0.0002

Data Index: 1534426 (Python Code)

Max Activating Token Index: 644

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1632. Min Act: -0.0002

Data Index: 1528703 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1604. Min Act: -0.0002

Data Index: 1633295 (Python Code)

Max Activating Token Index: 46

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1483379 (Python Code)

Max Activating Token Index: 400

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1574. Min Act: -0.0002

Data Index: 1539533 (Python Code)

Max Activating Token Index: 509

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1543. Min Act: -0.0002

Data Index: 1395425 (Python Code)

Max Activating Token Index: 81

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1581. Min Act: -0.0002

Data Index: 1380856 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1513. Min Act: -0.0002

Data Index: 1578263 (Python Code)

Max Activating Token Index: 219