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

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

Neuron 716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6987. Min Act: -0.0002

Data Index: 787992 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.7245. Min Act: -0.0001

Data Index: 1120285 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6892. Min Act: -0.0002

Data Index: 539405 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6819. Min Act: -0.0001

Data Index: 228488 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6760. Min Act: -0.0001

Data Index: 979913 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6344. Min Act: -0.0001

Data Index: 845812 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6689. Min Act: -0.0002

Data Index: 282555 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6479. Min Act: -0.0001

Data Index: 422339 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5541. Min Act: -0.0002

Data Index: 785555 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6435. Min Act: -0.0002

Data Index: 278209 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6212. Min Act: -0.0001

Data Index: 261574 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6649. Min Act: -0.0002

Data Index: 1074778 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6289. Min Act: -0.0002

Data Index: 923332 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5804. Min Act: -0.0001

Data Index: 540744 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5852. Min Act: -0.0001

Data Index: 1295923 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5570. Min Act: -0.0001

Data Index: 595771 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5567. Min Act: -0.0001

Data Index: 685298 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5396. Min Act: -0.0002

Data Index: 1199832 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1244363 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5785. Min Act: -0.0001

Data Index: 1207703 (C4 (Web Text))

Max Activating Token Index: 970