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

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

Neuron 3531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2766. Min Act: -0.0002

Data Index: 1432570 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2169. Min Act: -0.0002

Data Index: 1557052 (Python Code)

Max Activating Token Index: 927

Text #2

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1946. Min Act: -0.0002

Data Index: 1635293 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1887. Min Act: -0.0002

Data Index: 1590668 (Python Code)

Max Activating Token Index: 880

Text #4

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1925. Min Act: -0.0002

Data Index: 1470146 (Python Code)

Max Activating Token Index: 935

Text #5

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1729. Min Act: -0.0002

Data Index: 1525806 (Python Code)

Max Activating Token Index: 826

Text #6

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1766. Min Act: -0.0002

Data Index: 1461106 (Python Code)

Max Activating Token Index: 964

Text #7

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1753. Min Act: -0.0002

Data Index: 1458224 (Python Code)

Max Activating Token Index: 931

Text #8

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1751. Min Act: -0.0002

Data Index: 1634349 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1741. Min Act: -0.0002

Data Index: 1370480 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1803. Min Act: -0.0002

Data Index: 1442094 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1735. Min Act: -0.0002

Data Index: 1613025 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1810. Min Act: -0.0002

Data Index: 1628766 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1839. Min Act: -0.0002

Data Index: 1446160 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1746. Min Act: -0.0002

Data Index: 1479024 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1732. Min Act: -0.0002

Data Index: 1454883 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1790. Min Act: -0.0002

Data Index: 1459338 (Python Code)

Max Activating Token Index: 984

Text #17

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1655. Min Act: -0.0002

Data Index: 1523657 (Python Code)

Max Activating Token Index: 941

Text #18

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1637. Min Act: -0.0002

Data Index: 1501961 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.1692. Min Act: -0.0002

Data Index: 1466484 (Python Code)

Max Activating Token Index: 893