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

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

Neuron 525 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.2821. Min Act: -0.0000

Data Index: 582630 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1314778 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.2041. Min Act: -0.0001

Data Index: 524644 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1918. Min Act: -0.0001

Data Index: 781786 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1963. Min Act: -0.0001

Data Index: 849245 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1616. Min Act: -0.0001

Data Index: 230375 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1837. Min Act: -0.0000

Data Index: 324903 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1789. Min Act: -0.0001

Data Index: 550083 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1775. Min Act: -0.0000

Data Index: 599837 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1630. Min Act: -0.0000

Data Index: 817373 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1694. Min Act: -0.0001

Data Index: 24294 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1031839 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1759. Min Act: -0.0000

Data Index: 505014 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1887. Min Act: -0.0000

Data Index: 24608 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1520. Min Act: -0.0000

Data Index: 598656 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1644. Min Act: -0.0001

Data Index: 62907 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1294469 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1608. Min Act: -0.0001

Data Index: 800732 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1642. Min Act: -0.0000

Data Index: 3411 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.2821. Min Range: -0.2821

Max Act: 0.1568. Min Act: -0.0001

Data Index: 517918 (C4 (Web Text))

Max Activating Token Index: 258