Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3921 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1840. Min Act: -0.0000

Data Index: 602208 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1843. Min Act: -0.0001

Data Index: 527729 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1823. Min Act: -0.0000

Data Index: 816296 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1678. Min Act: -0.0000

Data Index: 627861 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1643. Min Act: -0.0000

Data Index: 546356 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1738. Min Act: -0.0001

Data Index: 134029 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1660. Min Act: -0.0001

Data Index: 171022 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1606. Min Act: -0.0001

Data Index: 433029 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1021240 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1662. Min Act: -0.0001

Data Index: 743939 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1556. Min Act: -0.0001

Data Index: 460558 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1499. Min Act: -0.0000

Data Index: 994678 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1485. Min Act: -0.0000

Data Index: 81739 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1497. Min Act: -0.0000

Data Index: 73677 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1597. Min Act: -0.0000

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1413. Min Act: -0.0001

Data Index: 472523 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1519. Min Act: -0.0001

Data Index: 160971 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1545. Min Act: -0.0000

Data Index: 393368 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1431. Min Act: -0.0000

Data Index: 401048 (C4 (Web Text))

Max Activating Token Index: 178