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

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

Neuron 559 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0642. Min Range: -1.0642

Max Act: 1.0642. Min Act: -0.0000

Data Index: 705003 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1317862 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1307677 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.8353. Min Act: -0.0000

Data Index: 384822 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.8050. Min Act: -0.0001

Data Index: 791107 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.7611. Min Act: -0.0000

Data Index: 424174 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.7222. Min Act: -0.0000

Data Index: 357903 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.7187. Min Act: -0.0001

Data Index: 193574 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.7118. Min Act: -0.0001

Data Index: 596078 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.7548. Min Act: -0.0000

Data Index: 113644 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1027285 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1115889 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1283121 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6812. Min Act: -0.0000

Data Index: 975045 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6757. Min Act: -0.0000

Data Index: 371581 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1351599 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6685. Min Act: -0.0000

Data Index: 882925 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6654. Min Act: -0.0001

Data Index: 1299187 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6580. Min Act: -0.0001

Data Index: 82820 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 1.0642. Min Range: -1.0642

Max Act: 0.6116. Min Act: -0.0001

Data Index: 501625 (C4 (Web Text))

Max Activating Token Index: 215