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

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

Neuron 2700 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.7592. Min Act: -0.0000

Data Index: 51890 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.7826. Min Act: -0.0000

Data Index: 492640 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6825. Min Act: -0.0000

Data Index: 921460 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6504. Min Act: -0.0000

Data Index: 471365 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1267180 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.7124. Min Act: -0.0000

Data Index: 838951 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6753. Min Act: -0.0000

Data Index: 589890 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6686. Min Act: -0.0000

Data Index: 435405 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6432. Min Act: -0.0000

Data Index: 365443 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6160. Min Act: -0.0000

Data Index: 132444 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6458. Min Act: -0.0000

Data Index: 798298 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6237. Min Act: -0.0000

Data Index: 584609 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.5705. Min Act: -0.0000

Data Index: 580270 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.5696. Min Act: -0.0000

Data Index: 208175 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1213055 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.5918. Min Act: -0.0000

Data Index: 341068 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.6027. Min Act: -0.0000

Data Index: 824819 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.5249. Min Act: -0.0000

Data Index: 809655 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.5553. Min Act: -0.0000

Data Index: 663596 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.7826. Min Range: -0.7826

Max Act: 0.5544. Min Act: -0.0000

Data Index: 816351 (C4 (Web Text))

Max Activating Token Index: 432