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

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

Neuron 3142 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: 1.9831. Min Range: -1.9831

Max Act: 1.9831. Min Act: -0.0000

Data Index: 1513869 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.6200. Min Act: -0.0000

Data Index: 1409895 (Python Code)

Max Activating Token Index: 765

Text #2

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1400430 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.5110. Min Act: -0.0000

Data Index: 1560190 (Python Code)

Max Activating Token Index: 554

Text #4

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1414415 (Python Code)

Max Activating Token Index: 233

Text #5

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.3295. Min Act: -0.0000

Data Index: 469837 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1452903 (Python Code)

Max Activating Token Index: 460

Text #7

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1383333 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.3303. Min Act: -0.0000

Data Index: 1425276 (Python Code)

Max Activating Token Index: 874

Text #9

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1433698 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1473111 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1636840 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1405172 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1403159 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1579500 (Python Code)

Max Activating Token Index: 270

Text #15

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1246267 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1514875 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.1919. Min Act: -0.0000

Data Index: 1301504 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1544237 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 1.9831. Min Range: -1.9831

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1587310 (Python Code)

Max Activating Token Index: 1014