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

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

Neuron 3446 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.9725. Min Act: -0.0001

Data Index: 1106755 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8789. Min Act: -0.0001

Data Index: 354715 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.9083. Min Act: -0.0001

Data Index: 463579 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8561. Min Act: -0.0002

Data Index: 90376 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8489. Min Act: -0.0002

Data Index: 132677 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8311. Min Act: -0.0001

Data Index: 1110668 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8708. Min Act: -0.0001

Data Index: 245147 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7309. Min Act: -0.0002

Data Index: 678725 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7758. Min Act: -0.0002

Data Index: 1051493 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7642. Min Act: -0.0002

Data Index: 1049597 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8039. Min Act: -0.0001

Data Index: 26461 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6813. Min Act: -0.0001

Data Index: 843241 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6905. Min Act: -0.0001

Data Index: 1287333 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.8038. Min Act: -0.0001

Data Index: 15155 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7606. Min Act: -0.0001

Data Index: 584414 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6249. Min Act: -0.0001

Data Index: 126226 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7073. Min Act: -0.0002

Data Index: 545991 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.7752. Min Act: -0.0002

Data Index: 701197 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6543. Min Act: -0.0002

Data Index: 517008 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.9725. Min Range: -0.9725

Max Act: 0.6704. Min Act: -0.0002

Data Index: 799541 (C4 (Web Text))

Max Activating Token Index: 186