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

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

Neuron 921 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0003

Data Index: 761656 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0966. Min Act: -0.0003

Data Index: 138311 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.1013. Min Act: -0.0003

Data Index: 4493 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0883. Min Act: -0.0003

Data Index: 322633 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0927. Min Act: -0.0003

Data Index: 888164 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0932. Min Act: -0.0003

Data Index: 409165 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0912. Min Act: -0.0003

Data Index: 611750 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0804. Min Act: -0.0003

Data Index: 300009 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0837. Min Act: -0.0003

Data Index: 29453 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1153640 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0816. Min Act: -0.0003

Data Index: 60333 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0846. Min Act: -0.0003

Data Index: 740118 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0790. Min Act: -0.0003

Data Index: 1212645 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0752. Min Act: -0.0003

Data Index: 670195 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0771. Min Act: -0.0003

Data Index: 854458 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0645. Min Act: -0.0003

Data Index: 614852 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0748. Min Act: -0.0003

Data Index: 608418 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0684. Min Act: -0.0003

Data Index: 357157 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0585. Min Act: -0.0003

Data Index: 430734 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0709. Min Act: -0.0003

Data Index: 221692 (C4 (Web Text))

Max Activating Token Index: 91