Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 227 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1072. Min Act: -0.0003

Data Index: 988916 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0003

Data Index: 673431 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1001. Min Act: -0.0003

Data Index: 1230439 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0876. Min Act: -0.0003

Data Index: 165191 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0878. Min Act: -0.0003

Data Index: 551318 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0830. Min Act: -0.0003

Data Index: 771943 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0854. Min Act: -0.0003

Data Index: 154307 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0800. Min Act: -0.0003

Data Index: 939025 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0835. Min Act: -0.0003

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0791. Min Act: -0.0003

Data Index: 1164526 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1282995 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0792. Min Act: -0.0003

Data Index: 937228 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0766. Min Act: -0.0003

Data Index: 1278115 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0849. Min Act: -0.0003

Data Index: 443050 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1152386 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0838. Min Act: -0.0003

Data Index: 646292 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0806. Min Act: -0.0003

Data Index: 58430 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0773. Min Act: -0.0003

Data Index: 1231073 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0785. Min Act: -0.0003

Data Index: 209028 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0741. Min Act: -0.0003

Data Index: 442933 (C4 (Web Text))

Max Activating Token Index: 828