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

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

Neuron 659 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.1843. Min Act: -0.0000

Data Index: 36189 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9593. Min Act: -0.0000

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9474. Min Act: -0.0000

Data Index: 930521 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 1.1843. Min Range: -1.1843

Max Act: 1.0153. Min Act: -0.0000

Data Index: 361317 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1209488 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9909. Min Act: -0.0000

Data Index: 550689 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.9317. Min Act: -0.0000

Data Index: 434872 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1160553 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7836. Min Act: -0.0000

Data Index: 337626 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7865. Min Act: -0.0000

Data Index: 771447 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.8039. Min Act: -0.0000

Data Index: 298973 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7704. Min Act: -0.0000

Data Index: 467358 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7523. Min Act: -0.0000

Data Index: 317025 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7593. Min Act: -0.0000

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.6972. Min Act: -0.0000

Data Index: 729952 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7107. Min Act: -0.0000

Data Index: 108152 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1650754 (Python Code)

Max Activating Token Index: 920

Text #17

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7215. Min Act: -0.0000

Data Index: 754149 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1064482 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.1843. Min Range: -1.1843

Max Act: 0.7458. Min Act: -0.0000

Data Index: 287989 (C4 (Web Text))

Max Activating Token Index: 432