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

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

Neuron 1159 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: 5.6829. Min Range: -5.6829

Max Act: 5.6829. Min Act: -0.0000

Data Index: 1612246 (Python Code)

Max Activating Token Index: 967

Text #1

Max Range: 5.6829. Min Range: -5.6829

Max Act: 5.0351. Min Act: -0.0000

Data Index: 1523741 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.7212. Min Act: -0.0000

Data Index: 1612667 (Python Code)

Max Activating Token Index: 496

Text #3

Max Range: 5.6829. Min Range: -5.6829

Max Act: 5.1915. Min Act: -0.0000

Data Index: 1530479 (Python Code)

Max Activating Token Index: 682

Text #4

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.8664. Min Act: -0.0000

Data Index: 1438369 (Python Code)

Max Activating Token Index: 353

Text #5

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.7883. Min Act: -0.0000

Data Index: 1522814 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.7052. Min Act: -0.0000

Data Index: 1611542 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.6323. Min Act: -0.0000

Data Index: 1622009 (Python Code)

Max Activating Token Index: 813

Text #8

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.3497. Min Act: -0.0000

Data Index: 1639247 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.3347. Min Act: -0.0000

Data Index: 1513751 (Python Code)

Max Activating Token Index: 129

Text #10

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.1269. Min Act: -0.0000

Data Index: 1471189 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.2931. Min Act: -0.0000

Data Index: 1491330 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.1236. Min Act: -0.0000

Data Index: 1502088 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.0852. Min Act: -0.0000

Data Index: 1624930 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 5.6829. Min Range: -5.6829

Max Act: 4.2309. Min Act: -0.0000

Data Index: 1460256 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.9252. Min Act: -0.0000

Data Index: 859474 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7257. Min Act: -0.0000

Data Index: 1575863 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7858. Min Act: -0.0000

Data Index: 1625642 (Python Code)

Max Activating Token Index: 1002

Text #18

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7296. Min Act: -0.0000

Data Index: 1610351 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 5.6829. Min Range: -5.6829

Max Act: 3.7255. Min Act: -0.0000

Data Index: 1635758 (Python Code)

Max Activating Token Index: 226