Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2461 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1884. Min Act: -0.0004

Data Index: 1525783 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1813. Min Act: -0.0004

Data Index: 1404538 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1811. Min Act: -0.0004

Data Index: 1623765 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1675. Min Act: -0.0004

Data Index: 1605242 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1771. Min Act: -0.0004

Data Index: 1499680 (Python Code)

Max Activating Token Index: 88

Text #5

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1709. Min Act: -0.0004

Data Index: 1573044 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1775. Min Act: -0.0004

Data Index: 1394553 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1690. Min Act: -0.0004

Data Index: 1403528 (Python Code)

Max Activating Token Index: 52

Text #8

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1744. Min Act: -0.0004

Data Index: 1429584 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1681. Min Act: -0.0004

Data Index: 1439754 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1689. Min Act: -0.0004

Data Index: 1481471 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1569. Min Act: -0.0004

Data Index: 1616360 (Python Code)

Max Activating Token Index: 385

Text #12

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1745. Min Act: -0.0004

Data Index: 1420949 (Python Code)

Max Activating Token Index: 142

Text #13

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1709. Min Act: -0.0004

Data Index: 1640087 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1643. Min Act: -0.0004

Data Index: 1496056 (Python Code)

Max Activating Token Index: 621

Text #15

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1564. Min Act: -0.0004

Data Index: 1462197 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1621. Min Act: -0.0004

Data Index: 1449005 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1688. Min Act: -0.0004

Data Index: 1399205 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1615. Min Act: -0.0004

Data Index: 1559715 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 0.1884. Min Range: -0.1884

Max Act: 0.1617. Min Act: -0.0004

Data Index: 1441304 (Python Code)

Max Activating Token Index: 26