Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1820 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0021. Min Act: -0.0002

Data Index: 528037 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 770471 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1039688 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 889360 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 437376 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1345835 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 231257 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 370466 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 869612 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1125715 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 515133 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 514846 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 1162059 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 860143 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 950349 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 1179963 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 978015 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 625148 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 8097 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 137048 (C4 (Web Text))

Max Activating Token Index: 878