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

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

Neuron 2010 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1259. Min Act: -0.0002

Data Index: 690061 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.1196. Min Act: -0.0002

Data Index: 823811 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0894. Min Act: -0.0002

Data Index: 661042 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0863. Min Act: -0.0002

Data Index: 406847 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0832. Min Act: -0.0002

Data Index: 266688 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0777. Min Act: -0.0002

Data Index: 80357 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0717. Min Act: -0.0002

Data Index: 363059 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0776. Min Act: -0.0002

Data Index: 763184 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0801. Min Act: -0.0002

Data Index: 261742 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1269086 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1337591 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0751. Min Act: -0.0002

Data Index: 312799 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0780. Min Act: -0.0002

Data Index: 91974 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1224449 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0730. Min Act: -0.0002

Data Index: 165467 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1075235 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0712. Min Act: -0.0002

Data Index: 310202 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0685. Min Act: -0.0002

Data Index: 358887 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0678. Min Act: -0.0002

Data Index: 484558 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1259. Min Range: -0.1259

Max Act: 0.0696. Min Act: -0.0002

Data Index: 470568 (C4 (Web Text))

Max Activating Token Index: 650