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

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

Neuron 2955 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1171. Min Range: -2.1171

Max Act: 2.1171. Min Act: -0.0000

Data Index: 104830 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.8704. Min Act: -0.0000

Data Index: 1246592 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.9995. Min Act: -0.0000

Data Index: 380494 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7797. Min Act: -0.0000

Data Index: 919419 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7525. Min Act: -0.0000

Data Index: 1044785 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.8207. Min Act: -0.0000

Data Index: 292615 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7088. Min Act: -0.0000

Data Index: 341559 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7908. Min Act: -0.0000

Data Index: 1297067 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.6817. Min Act: -0.0000

Data Index: 233053 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7553. Min Act: -0.0000

Data Index: 1311395 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7394. Min Act: -0.0000

Data Index: 828469 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7394. Min Act: -0.0000

Data Index: 843906 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.8214. Min Act: -0.0000

Data Index: 797765 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7010. Min Act: -0.0000

Data Index: 973965 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7010. Min Act: -0.0000

Data Index: 226228 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.6944. Min Act: -0.0000

Data Index: 1265196 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1000541 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7029. Min Act: -0.0000

Data Index: 310768 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.7845. Min Act: -0.0000

Data Index: 1105874 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.1171. Min Range: -2.1171

Max Act: 1.5764. Min Act: -0.0000

Data Index: 607273 (C4 (Web Text))

Max Activating Token Index: 643