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

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

Neuron 3761 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1915. Min Act: -0.0003

Data Index: 110846 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1877. Min Act: -0.0002

Data Index: 814017 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1904. Min Act: -0.0003

Data Index: 923061 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1832. Min Act: -0.0002

Data Index: 1018166 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1695. Min Act: -0.0003

Data Index: 923138 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1761. Min Act: -0.0002

Data Index: 343844 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1779. Min Act: -0.0003

Data Index: 1304722 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1748. Min Act: -0.0003

Data Index: 265692 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1744. Min Act: -0.0002

Data Index: 1227267 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1735. Min Act: -0.0003

Data Index: 236073 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1717. Min Act: -0.0003

Data Index: 524551 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1709. Min Act: -0.0002

Data Index: 1182492 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1683. Min Act: -0.0003

Data Index: 842231 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1611. Min Act: -0.0002

Data Index: 576071 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1711. Min Act: -0.0003

Data Index: 370607 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1645. Min Act: -0.0003

Data Index: 325874 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1589. Min Act: -0.0003

Data Index: 1309897 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1583. Min Act: -0.0002

Data Index: 1336871 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1631. Min Act: -0.0002

Data Index: 622116 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1684. Min Act: -0.0003

Data Index: 511893 (C4 (Web Text))

Max Activating Token Index: 38