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

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

Neuron 4101 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.6418. Min Act: -0.0000

Data Index: 1650459 (Python Code)

Max Activating Token Index: 696

Text #1

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.5731. Min Act: 0.0000

Data Index: 299074 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1564044 (Python Code)

Max Activating Token Index: 934

Text #3

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1485347 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1156869 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.1776. Min Act: -0.0000

Data Index: 794865 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.2073. Min Act: -0.0000

Data Index: 414034 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1360514 (Python Code)

Max Activating Token Index: 590

Text #8

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.0300. Min Act: -0.0000

Data Index: 1395876 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1563256 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.0740. Min Act: -0.0000

Data Index: 1646385 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1506917 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1555123 (Python Code)

Max Activating Token Index: 499

Text #13

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1503518 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1525243 (Python Code)

Max Activating Token Index: 421

Text #15

Max Range: 1.6418. Min Range: -1.6418

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1607177 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1524718 (Python Code)

Max Activating Token Index: 565

Text #17

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1585510 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.9492. Min Act: 0.0000

Data Index: 443283 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 1.6418. Min Range: -1.6418

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1653044 (Python Code)

Max Activating Token Index: 149