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

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

Neuron 3300 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1429557 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1643639 (Python Code)

Max Activating Token Index: 638

Text #2

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1634774 (Python Code)

Max Activating Token Index: 264

Text #3

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1555556 (Python Code)

Max Activating Token Index: 577

Text #4

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1621788 (Python Code)

Max Activating Token Index: 68

Text #5

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.1371. Min Act: -0.0000

Data Index: 1320101 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.2767. Min Act: -0.0001

Data Index: 1641062 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9201. Min Act: -0.0001

Data Index: 1239962 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1518812 (Python Code)

Max Activating Token Index: 468

Text #9

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1483237 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1408338 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1601524 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1570609 (Python Code)

Max Activating Token Index: 920

Text #13

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1507176 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1573132 (Python Code)

Max Activating Token Index: 726

Text #15

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1607905 (Python Code)

Max Activating Token Index: 555

Text #16

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9549. Min Act: -0.0001

Data Index: 1426507 (Python Code)

Max Activating Token Index: 635

Text #17

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1518120 (Python Code)

Max Activating Token Index: 337

Text #18

Max Range: 1.3374. Min Range: -1.3374

Max Act: 0.9970. Min Act: -0.0001

Data Index: 1418353 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 1.3374. Min Range: -1.3374

Max Act: 1.0580. Min Act: -0.0000

Data Index: 1479989 (Python Code)

Max Activating Token Index: 377