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

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

Neuron 451 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: 6.1762. Min Range: -6.1762

Max Act: 6.1762. Min Act: -0.0000

Data Index: 1560493 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 6.1762. Min Range: -6.1762

Max Act: 4.9365. Min Act: -0.0000

Data Index: 1434578 (Python Code)

Max Activating Token Index: 709

Text #2

Max Range: 6.1762. Min Range: -6.1762

Max Act: 4.6800. Min Act: -0.0000

Data Index: 1420961 (Python Code)

Max Activating Token Index: 276

Text #3

Max Range: 6.1762. Min Range: -6.1762

Max Act: 4.3745. Min Act: -0.0000

Data Index: 1627555 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 6.1762. Min Range: -6.1762

Max Act: 3.0927. Min Act: -0.0000

Data Index: 1385463 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 6.1762. Min Range: -6.1762

Max Act: 3.0926. Min Act: -0.0000

Data Index: 1428527 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.8409. Min Act: -0.0000

Data Index: 1491883 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.9728. Min Act: -0.0000

Data Index: 1372168 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.6796. Min Act: -0.0000

Data Index: 1365767 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.6953. Min Act: -0.0000

Data Index: 1385003 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.6850. Min Act: -0.0000

Data Index: 1553957 (Python Code)

Max Activating Token Index: 853

Text #11

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.4940. Min Act: -0.0000

Data Index: 1482549 (Python Code)

Max Activating Token Index: 704

Text #12

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.9966. Min Act: -0.0000

Data Index: 1362232 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.5438. Min Act: -0.0000

Data Index: 1520624 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.4176. Min Act: -0.0000

Data Index: 1580183 (Python Code)

Max Activating Token Index: 746

Text #15

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.6511. Min Act: -0.0000

Data Index: 1589790 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.6293. Min Act: -0.0000

Data Index: 1655215 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.6253. Min Act: -0.0000

Data Index: 1391620 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.5638. Min Act: -0.0000

Data Index: 1408068 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 6.1762. Min Range: -6.1762

Max Act: 2.5387. Min Act: -0.0000

Data Index: 1588632 (Python Code)

Max Activating Token Index: 977