Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5273 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.6558. Min Act: -0.0000

Data Index: 286659 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5800. Min Act: -0.0000

Data Index: 960688 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.5333. Min Act: -0.0000

Data Index: 446054 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4564. Min Act: -0.0000

Data Index: 926822 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4633. Min Act: -0.0000

Data Index: 59270 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4474. Min Act: -0.0000

Data Index: 470362 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1209384 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4553. Min Act: -0.0000

Data Index: 254747 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4463. Min Act: -0.0000

Data Index: 327965 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4328. Min Act: -0.0000

Data Index: 193902 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.4116. Min Act: -0.0000

Data Index: 298695 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3977. Min Act: -0.0000

Data Index: 44527 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3845. Min Act: -0.0000

Data Index: 246631 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3561. Min Act: -0.0000

Data Index: 273280 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3883. Min Act: -0.0000

Data Index: 564908 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3659. Min Act: -0.0000

Data Index: 513744 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3572. Min Act: -0.0000

Data Index: 124837 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1104508 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3750. Min Act: -0.0000

Data Index: 174522 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.6558. Min Range: -0.6558

Max Act: 0.3703. Min Act: -0.0000

Data Index: 952607 (C4 (Web Text))

Max Activating Token Index: 879