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

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

Neuron 606 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.6564. Min Act: -0.0000

Data Index: 408523 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.6210. Min Act: -0.0000

Data Index: 133362 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5955. Min Act: -0.0000

Data Index: 788950 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.6011. Min Act: -0.0000

Data Index: 973959 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5448. Min Act: -0.0000

Data Index: 103834 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5280. Min Act: -0.0000

Data Index: 657533 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5340. Min Act: -0.0000

Data Index: 548124 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5665. Min Act: -0.0000

Data Index: 516602 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1047032 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5229. Min Act: -0.0000

Data Index: 504951 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5710. Min Act: -0.0000

Data Index: 775517 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5532. Min Act: -0.0000

Data Index: 492688 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5319. Min Act: -0.0000

Data Index: 405126 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5209. Min Act: -0.0000

Data Index: 676442 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1036540 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1222252 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5735. Min Act: -0.0000

Data Index: 548004 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.4830. Min Act: -0.0000

Data Index: 844330 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5063. Min Act: -0.0000

Data Index: 894411 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.6564. Min Range: -0.6564

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1211433 (C4 (Web Text))

Max Activating Token Index: 832