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

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

Neuron 640 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: 0.0913. Min Range: -0.0913

Max Act: 0.0900. Min Act: -0.0003

Data Index: 534062 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1179850 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0803. Min Act: -0.0003

Data Index: 61088 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0003

Data Index: 1350066 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0837. Min Act: -0.0003

Data Index: 388754 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0803. Min Act: -0.0003

Data Index: 420725 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0764. Min Act: -0.0003

Data Index: 1252927 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0844. Min Act: -0.0003

Data Index: 684514 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0879. Min Act: -0.0003

Data Index: 432463 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0881. Min Act: -0.0003

Data Index: 129889 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0731. Min Act: -0.0003

Data Index: 912773 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0800. Min Act: -0.0003

Data Index: 795855 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0779. Min Act: -0.0003

Data Index: 507764 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1305578 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0813. Min Act: -0.0003

Data Index: 198634 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0775. Min Act: -0.0003

Data Index: 175202 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0721. Min Act: -0.0003

Data Index: 182893 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0750. Min Act: -0.0003

Data Index: 643869 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0725. Min Act: -0.0003

Data Index: 769535 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0766. Min Act: -0.0003

Data Index: 1178845 (C4 (Web Text))

Max Activating Token Index: 213