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

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

Neuron 3109 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.7412. Min Act: -0.0000

Data Index: 1362575 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.1425. Min Act: -0.0000

Data Index: 1633077 (Python Code)

Max Activating Token Index: 290

Text #2

Max Range: 2.7412. Min Range: -2.7412

Max Act: 1.9738. Min Act: -0.0000

Data Index: 1412755 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.2045. Min Act: -0.0000

Data Index: 1367668 (Python Code)

Max Activating Token Index: 210

Text #4

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.2008. Min Act: -0.0000

Data Index: 1581763 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.1814. Min Act: -0.0000

Data Index: 1605469 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.1789. Min Act: -0.0000

Data Index: 1613670 (Python Code)

Max Activating Token Index: 69

Text #7

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.3406. Min Act: -0.0000

Data Index: 1641448 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.1798. Min Act: -0.0000

Data Index: 1374682 (Python Code)

Max Activating Token Index: 519

Text #9

Max Range: 2.7412. Min Range: -2.7412

Max Act: 1.8828. Min Act: -0.0000

Data Index: 1500788 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.0411. Min Act: -0.0000

Data Index: 1654149 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.1353. Min Act: -0.0000

Data Index: 1544613 (Python Code)

Max Activating Token Index: 524

Text #12

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.0155. Min Act: -0.0000

Data Index: 1418376 (Python Code)

Max Activating Token Index: 199

Text #13

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.2036. Min Act: -0.0000

Data Index: 1471941 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.1109. Min Act: -0.0000

Data Index: 1509997 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.0623. Min Act: -0.0000

Data Index: 1402107 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.0510. Min Act: -0.0000

Data Index: 1550169 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.0954. Min Act: -0.0000

Data Index: 1476691 (Python Code)

Max Activating Token Index: 188

Text #18

Max Range: 2.7412. Min Range: -2.7412

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1647558 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 2.7412. Min Range: -2.7412

Max Act: 2.0640. Min Act: -0.0000

Data Index: 1603901 (Python Code)

Max Activating Token Index: 582