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

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

Neuron 3322 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: 1.1912. Min Range: -1.1912

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1613129 (Python Code)

Max Activating Token Index: 730

Text #1

Max Range: 1.1912. Min Range: -1.1912

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1554555 (Python Code)

Max Activating Token Index: 262

Text #2

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1477386 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1619527 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1526254 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1642675 (Python Code)

Max Activating Token Index: 527

Text #6

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1381503 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1458727 (Python Code)

Max Activating Token Index: 695

Text #8

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1408663 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1623818 (Python Code)

Max Activating Token Index: 745

Text #10

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1554593 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1361898 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1447585 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1573340 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1408169 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1372263 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1524758 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1403711 (Python Code)

Max Activating Token Index: 672

Text #18

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1650985 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 1.1912. Min Range: -1.1912

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1368393 (Python Code)

Max Activating Token Index: 856