Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2455 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3190. Min Range: -1.3190

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1498870 (Python Code)

Max Activating Token Index: 984

Text #1

Max Range: 1.3190. Min Range: -1.3190

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1597001 (Python Code)

Max Activating Token Index: 520

Text #2

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.9330. Min Act: -0.0000

Data Index: 1557952 (Python Code)

Max Activating Token Index: 773

Text #3

Max Range: 1.3190. Min Range: -1.3190

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1426803 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1625209 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1442463 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 1.3190. Min Range: -1.3190

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1624217 (Python Code)

Max Activating Token Index: 850

Text #7

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1447315 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1372462 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1435496 (Python Code)

Max Activating Token Index: 568

Text #10

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1413585 (Python Code)

Max Activating Token Index: 915

Text #11

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1567003 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1574041 (Python Code)

Max Activating Token Index: 123

Text #13

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1538705 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1369132 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1469591 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1396106 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1555639 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1376896 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 1.3190. Min Range: -1.3190

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1440804 (Python Code)

Max Activating Token Index: 710