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

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

Neuron 2133 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.8683. Min Act: -0.0003

Data Index: 1503194 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.8733. Min Act: -0.0003

Data Index: 1641507 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.8507. Min Act: -0.0002

Data Index: 1518376 (Python Code)

Max Activating Token Index: 821

Text #3

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.8300. Min Act: -0.0003

Data Index: 1436534 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.8134. Min Act: -0.0003

Data Index: 1631440 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7535. Min Act: -0.0003

Data Index: 1381380 (Python Code)

Max Activating Token Index: 271

Text #6

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7872. Min Act: -0.0003

Data Index: 1393605 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7971. Min Act: -0.0003

Data Index: 1488072 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7723. Min Act: -0.0003

Data Index: 1483098 (Python Code)

Max Activating Token Index: 256

Text #9

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7682. Min Act: -0.0003

Data Index: 1539901 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7663. Min Act: -0.0003

Data Index: 1648707 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7446. Min Act: -0.0003

Data Index: 1559179 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7439. Min Act: -0.0003

Data Index: 1557911 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7852. Min Act: -0.0003

Data Index: 1489147 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.6989. Min Act: -0.0003

Data Index: 1620856 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7168. Min Act: -0.0002

Data Index: 1436368 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7550. Min Act: -0.0003

Data Index: 1496984 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7705. Min Act: -0.0003

Data Index: 1454733 (Python Code)

Max Activating Token Index: 607

Text #18

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7102. Min Act: -0.0003

Data Index: 1383872 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 0.8733. Min Range: -0.8733

Max Act: 0.7068. Min Act: -0.0003

Data Index: 1523415 (Python Code)

Max Activating Token Index: 199