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

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

Neuron 1045 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1131. Min Act: -0.0002

Data Index: 737568 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1224364 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1034. Min Act: -0.0002

Data Index: 612157 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0987. Min Act: -0.0002

Data Index: 647637 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0937. Min Act: -0.0002

Data Index: 478457 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0909. Min Act: -0.0002

Data Index: 474723 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1064073 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0838. Min Act: -0.0002

Data Index: 395159 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0807. Min Act: -0.0002

Data Index: 908218 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0908. Min Act: -0.0002

Data Index: 193117 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0882. Min Act: -0.0002

Data Index: 400317 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0841. Min Act: -0.0002

Data Index: 232110 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1250941 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1358022 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0828. Min Act: -0.0002

Data Index: 480743 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1084319 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1263397 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0812. Min Act: -0.0002

Data Index: 945848 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0798. Min Act: -0.0002

Data Index: 549775 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1321061 (C4 (Web Text))

Max Activating Token Index: 941