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

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

Neuron 1471 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: 0.1162. Min Range: -0.1162

Max Act: 0.1162. Min Act: -0.0005

Data Index: 1016864 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1029. Min Act: -0.0005

Data Index: 1096373 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0931. Min Act: -0.0005

Data Index: 609977 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0927. Min Act: -0.0005

Data Index: 357920 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0914. Min Act: -0.0005

Data Index: 487861 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0929. Min Act: -0.0005

Data Index: 1324440 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0878. Min Act: -0.0005

Data Index: 28398 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0921. Min Act: -0.0005

Data Index: 405289 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0865. Min Act: -0.0005

Data Index: 1328314 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0899. Min Act: -0.0005

Data Index: 339992 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0863. Min Act: -0.0005

Data Index: 67649 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0867. Min Act: -0.0005

Data Index: 770228 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0785. Min Act: -0.0005

Data Index: 1027054 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0860. Min Act: -0.0005

Data Index: 966748 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0878. Min Act: -0.0005

Data Index: 996402 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0844. Min Act: -0.0005

Data Index: 1135316 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0869. Min Act: -0.0005

Data Index: 149650 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0841. Min Act: -0.0005

Data Index: 1248317 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0834. Min Act: -0.0005

Data Index: 592876 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0811. Min Act: -0.0005

Data Index: 97930 (C4 (Web Text))

Max Activating Token Index: 662