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

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

Neuron 3286 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: 0.5714. Min Range: -0.5714

Max Act: 0.5714. Min Act: -0.0000

Data Index: 32651 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.5042. Min Act: -0.0000

Data Index: 68387 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.4556. Min Act: -0.0000

Data Index: 742252 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1285611 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.4343. Min Act: -0.0000

Data Index: 767321 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.4208. Min Act: -0.0000

Data Index: 369919 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.4286. Min Act: -0.0000

Data Index: 782744 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3804. Min Act: -0.0000

Data Index: 790229 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.4108. Min Act: -0.0000

Data Index: 901488 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3745. Min Act: -0.0000

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3775. Min Act: -0.0000

Data Index: 968496 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1040185 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3567. Min Act: -0.0000

Data Index: 636241 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1127864 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3558. Min Act: -0.0000

Data Index: 282977 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3750. Min Act: -0.0000

Data Index: 215342 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3612. Min Act: -0.0000

Data Index: 751696 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3386. Min Act: -0.0000

Data Index: 81029 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1326313 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.5714. Min Range: -0.5714

Max Act: 0.3501. Min Act: -0.0000

Data Index: 613511 (C4 (Web Text))

Max Activating Token Index: 568