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

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

Neuron 903 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.4704. Min Act: -0.0000

Data Index: 265126 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.4247. Min Act: -0.0000

Data Index: 243831 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.3178. Min Act: -0.0000

Data Index: 799572 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.2837. Min Act: -0.0000

Data Index: 1017181 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1282210 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.1568. Min Act: -0.0000

Data Index: 590693 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.1596. Min Act: -0.0000

Data Index: 285465 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1052584 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.2006. Min Act: -0.0000

Data Index: 984572 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0811. Min Act: -0.0000

Data Index: 98266 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.1048. Min Act: -0.0000

Data Index: 63220 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0996. Min Act: -0.0000

Data Index: 732975 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0546. Min Act: -0.0000

Data Index: 522886 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0785. Min Act: -0.0000

Data Index: 417447 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0259. Min Act: -0.0000

Data Index: 249438 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0727. Min Act: -0.0000

Data Index: 725825 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.1598. Min Act: -0.0000

Data Index: 980689 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1044501 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0692. Min Act: -0.0000

Data Index: 887887 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.4704. Min Range: -1.4704

Max Act: 1.0385. Min Act: -0.0000

Data Index: 84449 (C4 (Web Text))

Max Activating Token Index: 532