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

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

Neuron 726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2170. Min Act: -0.0001

Data Index: 2695 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2062. Min Act: -0.0000

Data Index: 814527 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1775. Min Act: -0.0001

Data Index: 608 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1881. Min Act: -0.0001

Data Index: 817074 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1046612 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1153759 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1812. Min Act: -0.0001

Data Index: 596845 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1124653 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1679. Min Act: -0.0001

Data Index: 123148 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1645. Min Act: -0.0001

Data Index: 444374 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1509. Min Act: -0.0001

Data Index: 487256 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1390685 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1638. Min Act: -0.0001

Data Index: 858696 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1563. Min Act: -0.0001

Data Index: 444909 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1675. Min Act: -0.0001

Data Index: 558923 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1315094 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1445. Min Act: -0.0000

Data Index: 501014 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1524. Min Act: -0.0001

Data Index: 219841 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1531. Min Act: -0.0001

Data Index: 873370 (C4 (Web Text))

Max Activating Token Index: 617