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

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

Neuron 4361 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2876. Min Act: -0.0000

Data Index: 296655 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2113. Min Act: -0.0000

Data Index: 884247 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1995. Min Act: -0.0000

Data Index: 45677 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.2027. Min Act: -0.0000

Data Index: 680377 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1865. Min Act: -0.0000

Data Index: 104520 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1905. Min Act: -0.0000

Data Index: 215660 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1186841 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1812. Min Act: -0.0000

Data Index: 424352 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1043497 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1728. Min Act: -0.0000

Data Index: 324442 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1308373 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1117020 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1739. Min Act: -0.0000

Data Index: 27411 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1793. Min Act: -0.0000

Data Index: 832868 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1747. Min Act: -0.0000

Data Index: 919761 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1655. Min Act: -0.0000

Data Index: 55234 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1102641 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1743. Min Act: -0.0000

Data Index: 479185 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1729. Min Act: -0.0000

Data Index: 798197 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.2876. Min Range: -0.2876

Max Act: 0.1654. Min Act: -0.0000

Data Index: 932966 (C4 (Web Text))

Max Activating Token Index: 514