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

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

Neuron 3948 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0022. Min Act: -0.0003

Data Index: 402660 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0021. Min Act: -0.0003

Data Index: 604178 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0021. Min Act: -0.0003

Data Index: 469403 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0021. Min Act: -0.0003

Data Index: 700905 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0020. Min Act: -0.0002

Data Index: 1575106 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 847780 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0002

Data Index: 1381684 (Python Code)

Max Activating Token Index: 799

Text #7

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 783709 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0003

Data Index: 927202 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 793408 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 961723 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 709621 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 436847 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0003

Data Index: 734217 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 892871 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 1234334 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 105488 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0019. Min Act: -0.0003

Data Index: 1177670 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1642988 (Python Code)

Max Activating Token Index: 232

Text #19

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0018. Min Act: -0.0003

Data Index: 774373 (C4 (Web Text))

Max Activating Token Index: 827