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

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

Neuron 3493 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: 0.2845. Min Range: -0.2845

Max Act: 0.2819. Min Act: -0.0001

Data Index: 280615 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2845. Min Act: -0.0001

Data Index: 519515 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1041474 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1342212 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1154928 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1139171 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2080. Min Act: -0.0001

Data Index: 709005 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2045. Min Act: -0.0000

Data Index: 825734 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1224807 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1140382 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.2004. Min Act: -0.0001

Data Index: 658022 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1718. Min Act: -0.0001

Data Index: 265365 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1896. Min Act: -0.0001

Data Index: 727224 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1037373 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1767. Min Act: -0.0001

Data Index: 864638 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1770. Min Act: -0.0001

Data Index: 192059 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1847. Min Act: -0.0000

Data Index: 674877 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1650. Min Act: -0.0000

Data Index: 276987 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1708. Min Act: -0.0000

Data Index: 104698 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.2845. Min Range: -0.2845

Max Act: 0.1625. Min Act: -0.0000

Data Index: 262310 (C4 (Web Text))

Max Activating Token Index: 865