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

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

Neuron 5448 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0997. Min Act: -0.0001

Data Index: 823322 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0001

Data Index: 106036 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1354959 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1143859 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1934 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0889. Min Act: -0.0001

Data Index: 544148 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0982. Min Act: -0.0001

Data Index: 406825 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0922. Min Act: -0.0001

Data Index: 957319 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0951. Min Act: -0.0001

Data Index: 989539 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0907. Min Act: -0.0001

Data Index: 807537 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1237760 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1215697 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0868. Min Act: -0.0001

Data Index: 547863 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0893. Min Act: -0.0001

Data Index: 769138 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0854. Min Act: -0.0001

Data Index: 82124 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0827. Min Act: -0.0001

Data Index: 804435 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0859. Min Act: -0.0001

Data Index: 764506 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0829. Min Act: -0.0001

Data Index: 436859 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1219996 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1258733 (C4 (Web Text))

Max Activating Token Index: 1019