Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1654 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2064. Min Act: -0.0003

Data Index: 1565990 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2102. Min Act: -0.0004

Data Index: 1458516 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1914. Min Act: -0.0003

Data Index: 1391927 (Python Code)

Max Activating Token Index: 937

Text #3

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1979. Min Act: -0.0003

Data Index: 1559725 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1889. Min Act: -0.0003

Data Index: 1401170 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1925. Min Act: -0.0003

Data Index: 1603844 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1820. Min Act: -0.0003

Data Index: 1481222 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1878. Min Act: -0.0003

Data Index: 1433737 (Python Code)

Max Activating Token Index: 515

Text #8

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1809. Min Act: -0.0003

Data Index: 1502199 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1872. Min Act: -0.0003

Data Index: 1628254 (Python Code)

Max Activating Token Index: 721

Text #10

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1772. Min Act: -0.0003

Data Index: 1428209 (Python Code)

Max Activating Token Index: 736

Text #11

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1761. Min Act: -0.0003

Data Index: 1625763 (Python Code)

Max Activating Token Index: 706

Text #12

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1774. Min Act: -0.0003

Data Index: 1390327 (Python Code)

Max Activating Token Index: 429

Text #13

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1745. Min Act: -0.0003

Data Index: 1481099 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1734. Min Act: -0.0003

Data Index: 1579819 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1767. Min Act: -0.0002

Data Index: 1533461 (Python Code)

Max Activating Token Index: 252

Text #16

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1733. Min Act: -0.0002

Data Index: 1559705 (Python Code)

Max Activating Token Index: 688

Text #17

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1755. Min Act: -0.0003

Data Index: 1482465 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1725. Min Act: -0.0003

Data Index: 1577407 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1758. Min Act: -0.0003

Data Index: 1424791 (Python Code)

Max Activating Token Index: 676