Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0003

Data Index: 286717 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0774. Min Act: -0.0003

Data Index: 620017 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0701. Min Act: -0.0003

Data Index: 323853 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0760. Min Act: -0.0003

Data Index: 783826 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1274922 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1318108 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0662. Min Act: -0.0002

Data Index: 154357 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0698. Min Act: -0.0003

Data Index: 55040 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0666. Min Act: -0.0003

Data Index: 776962 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0625. Min Act: -0.0002

Data Index: 609784 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0698. Min Act: -0.0003

Data Index: 676471 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1200340 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0573. Min Act: -0.0003

Data Index: 526762 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0678. Min Act: -0.0003

Data Index: 438052 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0617. Min Act: -0.0003

Data Index: 16720 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0641. Min Act: -0.0003

Data Index: 438788 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1061995 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1017744 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1053573 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0616. Min Act: -0.0003

Data Index: 153253 (C4 (Web Text))

Max Activating Token Index: 11