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

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

Neuron 1472 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: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1068924 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2406. Min Act: -0.0000

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2186. Min Act: -0.0000

Data Index: 54565 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2092. Min Act: -0.0000

Data Index: 922385 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1090007 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1087675 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1976. Min Act: -0.0000

Data Index: 948985 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1952. Min Act: -0.0000

Data Index: 373978 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1855. Min Act: -0.0000

Data Index: 679897 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1872. Min Act: -0.0000

Data Index: 694642 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1813. Min Act: -0.0000

Data Index: 310932 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1771. Min Act: -0.0000

Data Index: 549391 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1759. Min Act: -0.0000

Data Index: 2237 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1055997 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1774. Min Act: -0.0000

Data Index: 280828 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1693. Min Act: -0.0000

Data Index: 318120 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1076146 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1347039 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1648. Min Act: -0.0000

Data Index: 477202 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1509548 (Python Code)

Max Activating Token Index: 440