Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 375 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1201. Min Act: -0.0001

Data Index: 311111 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1202. Min Act: -0.0001

Data Index: 656391 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1159. Min Act: -0.0001

Data Index: 279142 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1169. Min Act: -0.0001

Data Index: 334722 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1104. Min Act: -0.0001

Data Index: 616486 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1077. Min Act: -0.0001

Data Index: 747715 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1134926 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1066. Min Act: -0.0001

Data Index: 130594 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1056. Min Act: -0.0001

Data Index: 185484 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1121. Min Act: -0.0001

Data Index: 49597 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1092. Min Act: -0.0001

Data Index: 391415 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0999. Min Act: -0.0001

Data Index: 361982 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1065467 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1037. Min Act: -0.0001

Data Index: 846822 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1024. Min Act: -0.0001

Data Index: 335988 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1011. Min Act: -0.0001

Data Index: 94980 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1002. Min Act: -0.0001

Data Index: 940447 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1012. Min Act: -0.0001

Data Index: 684072 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1310444 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1026057 (C4 (Web Text))

Max Activating Token Index: 622