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

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

Neuron 3771 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: 0.3792. Min Range: -0.3792

Max Act: 0.3792. Min Act: -0.0001

Data Index: 317273 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3500. Min Act: -0.0001

Data Index: 520710 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3530. Min Act: -0.0001

Data Index: 594376 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3697. Min Act: -0.0001

Data Index: 1315740 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3566. Min Act: -0.0002

Data Index: 43482 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3197. Min Act: -0.0001

Data Index: 856381 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3222. Min Act: -0.0001

Data Index: 1269677 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3104. Min Act: -0.0001

Data Index: 756879 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3087. Min Act: -0.0001

Data Index: 722067 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3065. Min Act: -0.0001

Data Index: 1022168 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3053. Min Act: -0.0001

Data Index: 522732 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3054. Min Act: -0.0001

Data Index: 614235 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3080. Min Act: -0.0001

Data Index: 36031 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3231. Min Act: -0.0001

Data Index: 964872 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3009. Min Act: -0.0001

Data Index: 728333 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1240195 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1215103 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3071. Min Act: -0.0001

Data Index: 329872 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3249. Min Act: -0.0001

Data Index: 480731 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3014. Min Act: -0.0001

Data Index: 1288592 (C4 (Web Text))

Max Activating Token Index: 538