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

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

Neuron 4193 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: 0.7677. Min Range: -0.7677

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1399712 (Python Code)

Max Activating Token Index: 715

Text #1

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1626989 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1478220 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6914. Min Act: -0.0000

Data Index: 218831 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7133. Min Act: -0.0000

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1275644 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7045. Min Act: -0.0000

Data Index: 834535 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6764. Min Act: -0.0000

Data Index: 685758 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1413160 (Python Code)

Max Activating Token Index: 700

Text #9

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.7046. Min Act: -0.0000

Data Index: 144929 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6809. Min Act: -0.0000

Data Index: 935093 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6441. Min Act: -0.0000

Data Index: 668557 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6239. Min Act: -0.0000

Data Index: 112342 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6325. Min Act: -0.0000

Data Index: 955400 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1003994 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5927. Min Act: -0.0000

Data Index: 964155 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6141. Min Act: -0.0001

Data Index: 1380187 (Python Code)

Max Activating Token Index: 484

Text #17

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6644. Min Act: -0.0000

Data Index: 329867 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.5774. Min Act: -0.0000

Data Index: 845981 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.7677. Min Range: -0.7677

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1476141 (Python Code)

Max Activating Token Index: 674