Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2504 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0001

Data Index: 711859 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1021. Min Act: -0.0001

Data Index: 580792 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0968. Min Act: -0.0001

Data Index: 832629 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0950. Min Act: -0.0001

Data Index: 604794 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0838. Min Act: -0.0001

Data Index: 278449 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1234307 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1116699 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0811. Min Act: -0.0001

Data Index: 928247 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0818. Min Act: -0.0001

Data Index: 7234 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0819. Min Act: -0.0001

Data Index: 846036 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0799. Min Act: -0.0001

Data Index: 293927 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0819. Min Act: -0.0001

Data Index: 347944 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1248697 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0816. Min Act: -0.0001

Data Index: 336918 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0796. Min Act: -0.0001

Data Index: 635178 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0788. Min Act: -0.0001

Data Index: 799110 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0784. Min Act: -0.0001

Data Index: 167395 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0758. Min Act: -0.0001

Data Index: 834187 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0782. Min Act: -0.0001

Data Index: 354203 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0748. Min Act: -0.0001

Data Index: 520890 (C4 (Web Text))

Max Activating Token Index: 905