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

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

Neuron 2537 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5849. Min Range: -2.5849

Max Act: 2.5849. Min Act: -0.0000

Data Index: 514274 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.5849. Min Range: -2.5849

Max Act: 2.3929. Min Act: -0.0000

Data Index: 870131 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 2.5849. Min Range: -2.5849

Max Act: 2.3713. Min Act: -0.0000

Data Index: 881071 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.9915. Min Act: -0.0000

Data Index: 736199 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 2.5849. Min Range: -2.5849

Max Act: 2.0021. Min Act: -0.0000

Data Index: 1061093 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 2.5849. Min Range: -2.5849

Max Act: 2.1036. Min Act: -0.0000

Data Index: 760126 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.9410. Min Act: -0.0000

Data Index: 176254 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 2.5849. Min Range: -2.5849

Max Act: 2.0296. Min Act: -0.0000

Data Index: 482093 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1144420 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.8669. Min Act: -0.0000

Data Index: 296461 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.9675. Min Act: -0.0000

Data Index: 1039870 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.8227. Min Act: -0.0000

Data Index: 789914 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.8022. Min Act: -0.0000

Data Index: 785160 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.6907. Min Act: -0.0000

Data Index: 726128 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.7860. Min Act: -0.0000

Data Index: 1200405 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.7127. Min Act: -0.0000

Data Index: 752857 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.6923. Min Act: -0.0000

Data Index: 33634 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.6057. Min Act: -0.0000

Data Index: 1038470 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.6994. Min Act: -0.0000

Data Index: 512147 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 2.5849. Min Range: -2.5849

Max Act: 1.6077. Min Act: -0.0000

Data Index: 1141617 (C4 (Web Text))

Max Activating Token Index: 415