Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1201 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2014. Min Act: -0.0000

Data Index: 467602 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2075. Min Act: -0.0001

Data Index: 514189 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2200. Min Act: -0.0001

Data Index: 706680 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2190. Min Act: -0.0001

Data Index: 335070 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2047. Min Act: -0.0000

Data Index: 350380 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1325861 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1903. Min Act: -0.0001

Data Index: 562861 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1001759 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1068975 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1849. Min Act: -0.0000

Data Index: 64602 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1861. Min Act: -0.0001

Data Index: 848695 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1931. Min Act: -0.0000

Data Index: 657407 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1789. Min Act: -0.0001

Data Index: 994198 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1823. Min Act: -0.0001

Data Index: 457015 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1833. Min Act: -0.0000

Data Index: 290970 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1786. Min Act: -0.0000

Data Index: 626970 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1840. Min Act: -0.0001

Data Index: 329063 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1822. Min Act: -0.0000

Data Index: 299500 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1686. Min Act: -0.0001

Data Index: 514154 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.2200. Min Range: -0.2200

Max Act: 0.1651. Min Act: -0.0001

Data Index: 731130 (C4 (Web Text))

Max Activating Token Index: 851