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

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

Neuron 3553 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1593052 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1613188 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1561006 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1595397 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1577126 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1645398 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1653740 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1651297 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1461921 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1473853 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1600117 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1509218 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1396023 (Python Code)

Max Activating Token Index: 660

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1499121 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1391328 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1526864 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1405708 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1573115 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1523355 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1561949 (Python Code)

Max Activating Token Index: 786