Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2471 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.6850. Min Act: -0.0000

Data Index: 1559678 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.4888. Min Act: -0.0000

Data Index: 1623561 (Python Code)

Max Activating Token Index: 714

Text #2

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.4663. Min Act: -0.0000

Data Index: 1535871 (Python Code)

Max Activating Token Index: 825

Text #3

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.2254. Min Act: -0.0000

Data Index: 1650873 (Python Code)

Max Activating Token Index: 991

Text #4

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.3826. Min Act: -0.0000

Data Index: 1401261 (Python Code)

Max Activating Token Index: 578

Text #5

Max Range: 5.6850. Min Range: -5.6850

Max Act: 5.1303. Min Act: -0.0000

Data Index: 1457045 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.9252. Min Act: -0.0000

Data Index: 1508157 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.9763. Min Act: -0.0000

Data Index: 1526250 (Python Code)

Max Activating Token Index: 435

Text #8

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.9235. Min Act: -0.0000

Data Index: 1402555 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.8921. Min Act: -0.0000

Data Index: 1474934 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.8748. Min Act: -0.0000

Data Index: 1622129 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.6456. Min Act: -0.0000

Data Index: 1395368 (Python Code)

Max Activating Token Index: 765

Text #12

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.9770. Min Act: -0.0000

Data Index: 1580590 (Python Code)

Max Activating Token Index: 347

Text #13

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.9813. Min Act: -0.0000

Data Index: 1375586 (Python Code)

Max Activating Token Index: 527

Text #14

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.7902. Min Act: -0.0000

Data Index: 1586784 (Python Code)

Max Activating Token Index: 631

Text #15

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.8923. Min Act: -0.0000

Data Index: 1416005 (Python Code)

Max Activating Token Index: 1002

Text #16

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.7009. Min Act: -0.0000

Data Index: 1639060 (Python Code)

Max Activating Token Index: 629

Text #17

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.8706. Min Act: -0.0000

Data Index: 1393443 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.7012. Min Act: -0.0000

Data Index: 1623498 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 5.6850. Min Range: -5.6850

Max Act: 4.8298. Min Act: -0.0000

Data Index: 1488825 (Python Code)

Max Activating Token Index: 400