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

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

Neuron 791 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1642. Min Range: -3.1642

Max Act: 3.1642. Min Act: -0.0000

Data Index: 1502224 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.8807. Min Act: -0.0000

Data Index: 1431997 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.3735. Min Act: -0.0000

Data Index: 1450623 (Python Code)

Max Activating Token Index: 324

Text #3

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.1989. Min Act: -0.0000

Data Index: 1608184 (Python Code)

Max Activating Token Index: 710

Text #4

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.0525. Min Act: -0.0000

Data Index: 1476295 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.1478. Min Act: -0.0000

Data Index: 1433699 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.0188. Min Act: -0.0000

Data Index: 1476233 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.1468. Min Act: -0.0000

Data Index: 1565161 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.1446. Min Act: -0.0000

Data Index: 1467915 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1504277 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.3532. Min Act: -0.0000

Data Index: 1590082 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.9815. Min Act: -0.0000

Data Index: 1556584 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.0806. Min Act: -0.0000

Data Index: 1490948 (Python Code)

Max Activating Token Index: 395

Text #13

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.8411. Min Act: -0.0000

Data Index: 1600354 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.9357. Min Act: -0.0000

Data Index: 1544600 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.9396. Min Act: -0.0000

Data Index: 1650938 (Python Code)

Max Activating Token Index: 1002

Text #16

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.8260. Min Act: -0.0000

Data Index: 1390750 (Python Code)

Max Activating Token Index: 978

Text #17

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.8023. Min Act: -0.0000

Data Index: 1458600 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 3.1642. Min Range: -3.1642

Max Act: 1.9004. Min Act: -0.0000

Data Index: 1556587 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 3.1642. Min Range: -3.1642

Max Act: 2.0930. Min Act: -0.0000

Data Index: 1610842 (Python Code)

Max Activating Token Index: 801