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

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

Neuron 570 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2470. Min Act: -0.0001

Data Index: 346127 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1187748 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2010. Min Act: -0.0001

Data Index: 172870 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1988. Min Act: -0.0001

Data Index: 665308 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1111557 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1905. Min Act: -0.0001

Data Index: 299652 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1044826 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1829. Min Act: -0.0001

Data Index: 381890 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1811. Min Act: -0.0001

Data Index: 673640 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1782. Min Act: -0.0001

Data Index: 771583 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1791. Min Act: -0.0001

Data Index: 91313 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1867. Min Act: -0.0001

Data Index: 410099 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1650. Min Act: -0.0001

Data Index: 858816 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1761. Min Act: -0.0001

Data Index: 300033 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1492. Min Act: -0.0001

Data Index: 675997 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1315104 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1680. Min Act: -0.0001

Data Index: 199912 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1028441 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1755. Min Act: -0.0001

Data Index: 437226 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1656. Min Act: -0.0001

Data Index: 799446 (C4 (Web Text))

Max Activating Token Index: 196