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

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

Neuron 2539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5714. Min Act: -0.0001

Data Index: 862978 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.3881. Min Act: -0.0000

Data Index: 1151589 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1240168 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.3719. Min Act: -0.0000

Data Index: 457714 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.2615. Min Act: -0.0000

Data Index: 783796 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.2463. Min Act: -0.0000

Data Index: 759696 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1306368 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1529. Min Act: -0.0000

Data Index: 511630 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0052. Min Act: -0.0000

Data Index: 927757 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.2020. Min Act: -0.0000

Data Index: 1375033 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0864. Min Act: -0.0000

Data Index: 217265 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1342798 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0604. Min Act: -0.0000

Data Index: 746350 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1032165 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1224553 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0305. Min Act: -0.0000

Data Index: 940529 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0177. Min Act: -0.0000

Data Index: 933931 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1318239 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.5714. Min Range: -1.5714

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1571439 (Python Code)

Max Activating Token Index: 593

Text #19

Max Range: 1.5714. Min Range: -1.5714

Max Act: 0.9998. Min Act: -0.0000

Data Index: 129260 (C4 (Web Text))

Max Activating Token Index: 869