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

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

Neuron 4900 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: 1.3173. Min Range: -1.3173

Max Act: 1.1163. Min Act: -0.0000

Data Index: 12438 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.3173. Min Act: -0.0000

Data Index: 1014694 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.3173. Min Range: -1.3173

Max Act: 1.0201. Min Act: -0.0000

Data Index: 332713 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1115738 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.9649. Min Act: -0.0000

Data Index: 820879 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8496. Min Act: -0.0000

Data Index: 668588 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8373. Min Act: -0.0000

Data Index: 973282 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8709. Min Act: -0.0000

Data Index: 177131 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1211048 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1014408 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8326. Min Act: -0.0000

Data Index: 671248 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1319421 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1411863 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1212819 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1120744 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.7726. Min Act: -0.0000

Data Index: 809662 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1038836 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.7594. Min Act: -0.0000

Data Index: 598832 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.7768. Min Act: -0.0000

Data Index: 892551 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.3173. Min Range: -1.3173

Max Act: 0.7955. Min Act: -0.0000

Data Index: 793253 (C4 (Web Text))

Max Activating Token Index: 1016