Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3897 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1618070 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1344723 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1102940 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1008794 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0905. Min Act: -0.0000

Data Index: 772686 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1095876 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1026769 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0819. Min Act: -0.0001

Data Index: 120713 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0751. Min Act: -0.0000

Data Index: 272578 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0793. Min Act: -0.0001

Data Index: 589504 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0792. Min Act: -0.0000

Data Index: 593803 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0771. Min Act: -0.0000

Data Index: 988764 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0663. Min Act: -0.0001

Data Index: 479915 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1043133 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1652274 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0759. Min Act: -0.0001

Data Index: 364167 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0761. Min Act: -0.0000

Data Index: 261457 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0754. Min Act: -0.0000

Data Index: 978677 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0748. Min Act: -0.0000

Data Index: 866360 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0754. Min Act: -0.0001

Data Index: 31983 (C4 (Web Text))

Max Activating Token Index: 521