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

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

Neuron 3221 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.3868. Min Act: -0.0000

Data Index: 1652434 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1426. Min Act: -0.0000

Data Index: 1370105 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.2003. Min Act: -0.0000

Data Index: 1593169 (Python Code)

Max Activating Token Index: 499

Text #3

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1556635 (Python Code)

Max Activating Token Index: 199

Text #4

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.0848. Min Act: -0.0000

Data Index: 1509618 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1566097 (Python Code)

Max Activating Token Index: 142

Text #6

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1529289 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1648703 (Python Code)

Max Activating Token Index: 42

Text #8

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1631868 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1561793 (Python Code)

Max Activating Token Index: 1022

Text #10

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.0836. Min Act: -0.0000

Data Index: 1580483 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1444645 (Python Code)

Max Activating Token Index: 747

Text #12

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9643. Min Act: 0.0001

Data Index: 1571860 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1443534 (Python Code)

Max Activating Token Index: 637

Text #14

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1522870 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1435322 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1589904 (Python Code)

Max Activating Token Index: 594

Text #17

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9008. Min Act: 0.0000

Data Index: 1613309 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1601105 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1519791 (Python Code)

Max Activating Token Index: 326