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

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

Neuron 2694 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0680. Min Range: -2.0680

Max Act: 2.0680. Min Act: -0.0000

Data Index: 1147682 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.9964. Min Act: -0.0000

Data Index: 40452 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.9546. Min Act: -0.0000

Data Index: 126389 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 2.0680. Min Range: -2.0680

Max Act: 2.0418. Min Act: -0.0000

Data Index: 68098 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.7237. Min Act: -0.0000

Data Index: 1071694 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.7710. Min Act: -0.0000

Data Index: 805356 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6668. Min Act: -0.0000

Data Index: 1018343 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6963. Min Act: -0.0000

Data Index: 502812 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6831. Min Act: -0.0000

Data Index: 1138898 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6795. Min Act: -0.0000

Data Index: 548310 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.7211. Min Act: -0.0000

Data Index: 376792 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6679. Min Act: -0.0000

Data Index: 64916 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.5674. Min Act: -0.0000

Data Index: 939669 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6998. Min Act: -0.0000

Data Index: 202700 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6453. Min Act: -0.0000

Data Index: 990460 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6780. Min Act: -0.0000

Data Index: 1061458 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6129. Min Act: -0.0000

Data Index: 300554 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.5688. Min Act: -0.0000

Data Index: 1050185 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1112219 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 2.0680. Min Range: -2.0680

Max Act: 1.6051. Min Act: -0.0000

Data Index: 336906 (C4 (Web Text))

Max Activating Token Index: 948