Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1007 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5072. Min Range: -3.5072

Max Act: 3.5072. Min Act: -0.0000

Data Index: 1571160 (Python Code)

Max Activating Token Index: 371

Text #1

Max Range: 3.5072. Min Range: -3.5072

Max Act: 3.3663. Min Act: -0.0000

Data Index: 1495215 (Python Code)

Max Activating Token Index: 451

Text #2

Max Range: 3.5072. Min Range: -3.5072

Max Act: 3.1441. Min Act: -0.0000

Data Index: 1442695 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 3.5072. Min Range: -3.5072

Max Act: 3.2595. Min Act: -0.0000

Data Index: 1564747 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 3.5072. Min Range: -3.5072

Max Act: 3.0095. Min Act: -0.0000

Data Index: 1537339 (Python Code)

Max Activating Token Index: 658

Text #5

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.8364. Min Act: -0.0000

Data Index: 1391172 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.8187. Min Act: -0.0000

Data Index: 1446897 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.8804. Min Act: -0.0000

Data Index: 1370512 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.7093. Min Act: -0.0000

Data Index: 1508492 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.7222. Min Act: -0.0000

Data Index: 1582303 (Python Code)

Max Activating Token Index: 68

Text #10

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.4672. Min Act: -0.0000

Data Index: 1521262 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.7102. Min Act: -0.0000

Data Index: 1446539 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.5650. Min Act: -0.0000

Data Index: 1478665 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.3616. Min Act: -0.0000

Data Index: 1639324 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.3398. Min Act: -0.0000

Data Index: 1431644 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.2261. Min Act: -0.0000

Data Index: 1487226 (Python Code)

Max Activating Token Index: 496

Text #16

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.3379. Min Act: -0.0000

Data Index: 1474193 (Python Code)

Max Activating Token Index: 554

Text #17

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.3672. Min Act: -0.0000

Data Index: 1607177 (Python Code)

Max Activating Token Index: 972

Text #18

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.0921. Min Act: -0.0000

Data Index: 1560611 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 3.5072. Min Range: -3.5072

Max Act: 2.1891. Min Act: -0.0000

Data Index: 1390855 (Python Code)

Max Activating Token Index: 273