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

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

Neuron 6086 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: 2.3180. Min Range: -2.3180

Max Act: 2.3180. Min Act: -0.0000

Data Index: 1599338 (Python Code)

Max Activating Token Index: 322

Text #1

Max Range: 2.3180. Min Range: -2.3180

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1640532 (Python Code)

Max Activating Token Index: 327

Text #2

Max Range: 2.3180. Min Range: -2.3180

Max Act: 2.1887. Min Act: -0.0000

Data Index: 1624102 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 2.3180. Min Range: -2.3180

Max Act: 2.1526. Min Act: -0.0000

Data Index: 1590936 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 2.3180. Min Range: -2.3180

Max Act: 2.0564. Min Act: -0.0000

Data Index: 1509519 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.9667. Min Act: -0.0000

Data Index: 1430009 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.8789. Min Act: -0.0000

Data Index: 1527016 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.8765. Min Act: -0.0000

Data Index: 1557663 (Python Code)

Max Activating Token Index: 837

Text #8

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.8569. Min Act: -0.0000

Data Index: 1415173 (Python Code)

Max Activating Token Index: 336

Text #9

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.8417. Min Act: -0.0000

Data Index: 1414780 (Python Code)

Max Activating Token Index: 271

Text #10

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.8021. Min Act: -0.0000

Data Index: 1520364 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1581268 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.6858. Min Act: -0.0000

Data Index: 1592443 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.6575. Min Act: -0.0000

Data Index: 1605324 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1603836 (Python Code)

Max Activating Token Index: 1017

Text #15

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1366172 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.6812. Min Act: -0.0000

Data Index: 1423548 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.6750. Min Act: -0.0000

Data Index: 1492232 (Python Code)

Max Activating Token Index: 259

Text #18

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.5678. Min Act: -0.0000

Data Index: 1511713 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 2.3180. Min Range: -2.3180

Max Act: 1.6353. Min Act: -0.0000

Data Index: 1619421 (Python Code)

Max Activating Token Index: 613