Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1708 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.9649. Min Act: -0.0000

Data Index: 248334 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.8794. Min Act: -0.0000

Data Index: 787892 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7571. Min Act: -0.0000

Data Index: 461107 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7270. Min Act: -0.0001

Data Index: 66094 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6927. Min Act: -0.0000

Data Index: 412469 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6412. Min Act: -0.0001

Data Index: 735549 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6771. Min Act: -0.0000

Data Index: 341822 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1040489 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6839. Min Act: -0.0000

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7063. Min Act: -0.0000

Data Index: 47213 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6822. Min Act: -0.0000

Data Index: 511433 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6172. Min Act: -0.0000

Data Index: 491275 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7067. Min Act: -0.0001

Data Index: 1326193 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1009439 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1267390 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6760. Min Act: -0.0000

Data Index: 811650 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6955. Min Act: -0.0000

Data Index: 577362 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.7216. Min Act: -0.0001

Data Index: 750048 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1090159 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.9649. Min Range: -0.9649

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1235730 (C4 (Web Text))

Max Activating Token Index: 133