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

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

Neuron 3387 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1405748 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1627532 (Python Code)

Max Activating Token Index: 580

Text #2

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2150. Min Act: -0.0001

Data Index: 1523443 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1555768 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1607965 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1513905 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1450108 (Python Code)

Max Activating Token Index: 496

Text #7

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1644080 (Python Code)

Max Activating Token Index: 775

Text #8

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1466382 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1526208 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1564272 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1369772 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1393058 (Python Code)

Max Activating Token Index: 274

Text #13

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1518670 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1712. Min Act: -0.0001

Data Index: 1583097 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1401714 (Python Code)

Max Activating Token Index: 754

Text #16

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1475596 (Python Code)

Max Activating Token Index: 366

Text #17

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1427041 (Python Code)

Max Activating Token Index: 496

Text #18

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1419385 (Python Code)

Max Activating Token Index: 228

Text #19

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1615000 (Python Code)

Max Activating Token Index: 318