Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 328 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0005

Data Index: 1013711 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0843. Min Act: -0.0005

Data Index: 177894 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0852. Min Act: -0.0005

Data Index: 667879 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0802. Min Act: -0.0005

Data Index: 785176 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0868. Min Act: -0.0005

Data Index: 560014 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0753. Min Act: -0.0005

Data Index: 300850 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0784. Min Act: -0.0005

Data Index: 1140442 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0765. Min Act: -0.0005

Data Index: 312117 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0750. Min Act: -0.0005

Data Index: 871817 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0732. Min Act: -0.0005

Data Index: 1311050 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0760. Min Act: -0.0005

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0791. Min Act: -0.0005

Data Index: 370953 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0757. Min Act: -0.0005

Data Index: 111384 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0759. Min Act: -0.0005

Data Index: 1310128 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0760. Min Act: -0.0005

Data Index: 427319 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0717. Min Act: -0.0005

Data Index: 1208959 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0723. Min Act: -0.0005

Data Index: 282983 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0724. Min Act: -0.0005

Data Index: 1082743 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0741. Min Act: -0.0005

Data Index: 305813 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0765. Min Act: -0.0005

Data Index: 186505 (C4 (Web Text))

Max Activating Token Index: 109