Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1171 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.5205. Min Act: -0.0000

Data Index: 102669 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.3505. Min Act: -0.0000

Data Index: 574901 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.3636. Min Act: -0.0000

Data Index: 199472 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.4145. Min Act: -0.0000

Data Index: 829626 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.3144. Min Act: -0.0000

Data Index: 633791 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2888. Min Act: -0.0000

Data Index: 637471 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1275024 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2744. Min Act: -0.0000

Data Index: 899376 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1695. Min Act: -0.0000

Data Index: 479549 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.3021. Min Act: -0.0000

Data Index: 519501 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2212. Min Act: -0.0000

Data Index: 482693 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2026. Min Act: -0.0000

Data Index: 649784 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2801. Min Act: -0.0000

Data Index: 1357484 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2627. Min Act: -0.0000

Data Index: 890161 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1818. Min Act: -0.0000

Data Index: 44830 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1183767 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1088344 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.1412. Min Act: -0.0000

Data Index: 1014917 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1129297 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.5205. Min Range: -1.5205

Max Act: 1.0949. Min Act: -0.0000

Data Index: 65885 (C4 (Web Text))

Max Activating Token Index: 273