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

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

Neuron 2571 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1453669 (Python Code)

Max Activating Token Index: 822

Text #1

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1468022 (Python Code)

Max Activating Token Index: 597

Text #2

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4332. Min Act: -0.0000

Data Index: 1416978 (Python Code)

Max Activating Token Index: 837

Text #3

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4955. Min Act: -0.0000

Data Index: 1404996 (Python Code)

Max Activating Token Index: 638

Text #4

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4534. Min Act: -0.0000

Data Index: 1595312 (Python Code)

Max Activating Token Index: 607

Text #5

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1533202 (Python Code)

Max Activating Token Index: 800

Text #6

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1457057 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4272. Min Act: -0.0000

Data Index: 1479123 (Python Code)

Max Activating Token Index: 811

Text #8

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1620098 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1445153 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1489904 (Python Code)

Max Activating Token Index: 839

Text #11

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1494930 (Python Code)

Max Activating Token Index: 923

Text #12

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1649722 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1368973 (Python Code)

Max Activating Token Index: 561

Text #14

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1435263 (Python Code)

Max Activating Token Index: 767

Text #15

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1603801 (Python Code)

Max Activating Token Index: 132

Text #16

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1401431 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1644883 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1535160 (Python Code)

Max Activating Token Index: 516

Text #19

Max Range: 1.5453. Min Range: -1.5453

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1392505 (Python Code)

Max Activating Token Index: 305