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

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

Neuron 3606 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8737. Min Act: -0.0000

Data Index: 746681 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1040610 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7587. Min Act: -0.0000

Data Index: 128257 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6833. Min Act: -0.0000

Data Index: 675895 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1207459 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7697. Min Act: -0.0000

Data Index: 59058 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6785. Min Act: -0.0000

Data Index: 801465 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6391. Min Act: -0.0000

Data Index: 424035 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6329. Min Act: -0.0000

Data Index: 330346 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6543. Min Act: -0.0000

Data Index: 857865 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6274. Min Act: -0.0000

Data Index: 368514 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5975. Min Act: -0.0000

Data Index: 991177 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1073909 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5774. Min Act: -0.0000

Data Index: 791764 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6049. Min Act: -0.0000

Data Index: 294237 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6375. Min Act: -0.0000

Data Index: 444208 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5706. Min Act: 0.0000

Data Index: 88550 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1333864 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5885. Min Act: -0.0000

Data Index: 856630 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5669. Min Act: -0.0000

Data Index: 51932 (C4 (Web Text))

Max Activating Token Index: 477