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

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

Neuron 63 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1727. Min Range: -1.1727

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1288134 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.9368. Min Act: -0.0000

Data Index: 408740 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.1727. Min Range: -1.1727

Max Act: 1.0245. Min Act: -0.0000

Data Index: 570421 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.9711. Min Act: -0.0000

Data Index: 298804 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8774. Min Act: -0.0000

Data Index: 500244 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8446. Min Act: -0.0000

Data Index: 109171 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7170. Min Act: -0.0000

Data Index: 195429 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8417. Min Act: -0.0000

Data Index: 648664 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7844. Min Act: -0.0000

Data Index: 430673 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8085. Min Act: -0.0000

Data Index: 319523 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7804. Min Act: -0.0000

Data Index: 614859 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8212. Min Act: -0.0000

Data Index: 452441 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8198. Min Act: -0.0000

Data Index: 525965 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6853. Min Act: -0.0000

Data Index: 439316 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1334866 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7699. Min Act: -0.0000

Data Index: 228678 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7545. Min Act: -0.0000

Data Index: 665225 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1186882 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1076789 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7403. Min Act: -0.0000

Data Index: 875432 (C4 (Web Text))

Max Activating Token Index: 729