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

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

Neuron 3101 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 1276593 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 22798 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 333476 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 645817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 768432 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 377166 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 998628 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 865468 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1027209 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 1232995 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1091982 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 212616 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 450797 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 394034 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 850836 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 529938 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 53749 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 760599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 537536 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 3705 (C4 (Web Text))

Max Activating Token Index: 856