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

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

Neuron 2506 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: 2.2116. Min Range: -2.2116

Max Act: 2.2116. Min Act: -0.0000

Data Index: 1459000 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.0534. Min Act: -0.0000

Data Index: 1615161 (Python Code)

Max Activating Token Index: 494

Text #2

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.1018. Min Act: -0.0000

Data Index: 1523392 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.0895. Min Act: -0.0000

Data Index: 1596963 (Python Code)

Max Activating Token Index: 209

Text #4

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.1812. Min Act: -0.0000

Data Index: 1424268 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9560. Min Act: -0.0000

Data Index: 1487490 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.0628. Min Act: -0.0000

Data Index: 1614924 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.0596. Min Act: -0.0000

Data Index: 1436872 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.8504. Min Act: -0.0000

Data Index: 1445272 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9252. Min Act: -0.0000

Data Index: 1521057 (Python Code)

Max Activating Token Index: 91

Text #10

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9905. Min Act: -0.0000

Data Index: 1394714 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9837. Min Act: -0.0000

Data Index: 1485524 (Python Code)

Max Activating Token Index: 218

Text #12

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9789. Min Act: -0.0000

Data Index: 1496580 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.0797. Min Act: -0.0000

Data Index: 1558750 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1642234 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.8563. Min Act: -0.0000

Data Index: 1396650 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9596. Min Act: -0.0000

Data Index: 1638322 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9614. Min Act: -0.0000

Data Index: 1400913 (Python Code)

Max Activating Token Index: 699

Text #18

Max Range: 2.2116. Min Range: -2.2116

Max Act: 1.9657. Min Act: -0.0000

Data Index: 1478357 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 2.2116. Min Range: -2.2116

Max Act: 2.0687. Min Act: -0.0000

Data Index: 1419167 (Python Code)

Max Activating Token Index: 430