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

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

Neuron 1438 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8718. Min Act: -0.0001

Data Index: 140553 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8984. Min Act: -0.0001

Data Index: 857276 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8788. Min Act: -0.0001

Data Index: 1291602 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7917. Min Act: -0.0001

Data Index: 636526 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7948. Min Act: -0.0001

Data Index: 294762 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7526. Min Act: -0.0001

Data Index: 1213234 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8028. Min Act: -0.0001

Data Index: 123270 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8026. Min Act: -0.0001

Data Index: 358027 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7551. Min Act: -0.0001

Data Index: 905554 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7973. Min Act: -0.0001

Data Index: 1084133 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7375. Min Act: -0.0001

Data Index: 197781 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7689. Min Act: -0.0001

Data Index: 1033285 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7572. Min Act: -0.0001

Data Index: 642916 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7530. Min Act: -0.0001

Data Index: 522934 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7933. Min Act: -0.0001

Data Index: 1136206 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7516. Min Act: -0.0001

Data Index: 1177247 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7696. Min Act: -0.0001

Data Index: 484768 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1031153 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6892. Min Act: -0.0001

Data Index: 178839 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8107. Min Act: -0.0001

Data Index: 1068450 (C4 (Web Text))

Max Activating Token Index: 998