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

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

Neuron 2643 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0105. Min Range: -1.0105

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1155428 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.9393. Min Act: -0.0000

Data Index: 462329 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8788. Min Act: -0.0000

Data Index: 526527 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1063998 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8185. Min Act: -0.0000

Data Index: 165436 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8474. Min Act: -0.0000

Data Index: 810970 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.9070. Min Act: -0.0000

Data Index: 324647 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7283. Min Act: -0.0000

Data Index: 32811 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.8223. Min Act: -0.0000

Data Index: 48242 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7486. Min Act: -0.0000

Data Index: 394979 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7300. Min Act: -0.0000

Data Index: 324126 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7481. Min Act: -0.0000

Data Index: 174193 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7717. Min Act: -0.0000

Data Index: 542748 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7033. Min Act: -0.0000

Data Index: 452226 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7063. Min Act: -0.0000

Data Index: 936121 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7223. Min Act: -0.0000

Data Index: 603934 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6860. Min Act: -0.0000

Data Index: 825763 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.6929. Min Act: -0.0000

Data Index: 439202 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1029770 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 1.0105. Min Range: -1.0105

Max Act: 0.7364. Min Act: -0.0000

Data Index: 285823 (C4 (Web Text))

Max Activating Token Index: 492