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

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

Neuron 4724 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: 0.2180. Min Range: -0.2180

Max Act: 0.2173. Min Act: -0.0000

Data Index: 806824 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.2180. Min Act: 0.0000

Data Index: 292421 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.2051. Min Act: -0.0000

Data Index: 190782 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.2009. Min Act: -0.0000

Data Index: 272392 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.2050. Min Act: -0.0000

Data Index: 724714 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.2046. Min Act: -0.0000

Data Index: 222791 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1099797 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1892. Min Act: -0.0000

Data Index: 478525 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1818. Min Act: -0.0000

Data Index: 956289 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1825. Min Act: -0.0000

Data Index: 769349 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1225067 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1863. Min Act: -0.0000

Data Index: 131220 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1088896 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1322512 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1139635 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1798. Min Act: -0.0000

Data Index: 383909 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1000671 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1203509 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1706. Min Act: -0.0000

Data Index: 907774 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1753. Min Act: -0.0000

Data Index: 351063 (C4 (Web Text))

Max Activating Token Index: 462