Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4861 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.3200. Min Act: -0.0000

Data Index: 584987 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.1124. Min Act: -0.0000

Data Index: 856500 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1314496 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1351138 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.0672. Min Act: -0.0000

Data Index: 350818 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9212. Min Act: -0.0000

Data Index: 420061 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9709. Min Act: -0.0000

Data Index: 23574 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9744. Min Act: -0.0000

Data Index: 452749 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9583. Min Act: -0.0000

Data Index: 775280 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9574. Min Act: 0.0001

Data Index: 8753 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.0139. Min Act: 0.0000

Data Index: 540636 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9379. Min Act: -0.0000

Data Index: 270018 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 1.3200. Min Range: -1.3200

Max Act: 1.0023. Min Act: -0.0000

Data Index: 343229 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9323. Min Act: -0.0000

Data Index: 77637 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9753. Min Act: -0.0000

Data Index: 678703 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9165. Min Act: 0.0000

Data Index: 1326510 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9070. Min Act: -0.0000

Data Index: 241052 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9000. Min Act: -0.0000

Data Index: 169624 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1015549 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 1.3200. Min Range: -1.3200

Max Act: 0.9025. Min Act: -0.0000

Data Index: 625191 (C4 (Web Text))

Max Activating Token Index: 214