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

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

Neuron 4170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2848. Min Act: -0.0000

Data Index: 1475395 (Python Code)

Max Activating Token Index: 444

Text #1

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2406. Min Act: -0.0000

Data Index: 82231 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1633. Min Act: -0.0000

Data Index: 1413466 (Python Code)

Max Activating Token Index: 792

Text #3

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.9578. Min Act: -0.0000

Data Index: 1589125 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1620. Min Act: -0.0000

Data Index: 78452 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.9681. Min Act: -0.0000

Data Index: 1505480 (Python Code)

Max Activating Token Index: 942

Text #6

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.1089. Min Act: -0.0000

Data Index: 1404436 (Python Code)

Max Activating Token Index: 794

Text #7

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.7637. Min Act: -0.0000

Data Index: 353105 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.0383. Min Act: -0.0000

Data Index: 1581868 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.2613. Min Act: -0.0000

Data Index: 806236 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.3412. Min Act: -0.0000

Data Index: 1611698 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.3491. Min Act: -0.0000

Data Index: 1449960 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.9951. Min Act: -0.0000

Data Index: 1455551 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.0349. Min Act: -0.0000

Data Index: 1479510 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.7218. Min Act: -0.0000

Data Index: 1463030 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.8575. Min Act: -0.0000

Data Index: 1368661 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 3.3491. Min Range: -3.3491

Max Act: 3.0090. Min Act: -0.0000

Data Index: 1381743 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.7046. Min Act: -0.0000

Data Index: 1576980 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.7798. Min Act: -0.0000

Data Index: 1650525 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 3.3491. Min Range: -3.3491

Max Act: 2.7267. Min Act: -0.0000

Data Index: 1519861 (Python Code)

Max Activating Token Index: 721