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

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

Neuron 3076 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: 2.6237. Min Range: -2.6237

Max Act: 2.3763. Min Act: -0.0000

Data Index: 273432 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.6237. Min Act: -0.0000

Data Index: 969371 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.5176. Min Act: -0.0000

Data Index: 219375 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.5646. Min Act: -0.0000

Data Index: 901829 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.6086. Min Act: -0.0000

Data Index: 1200997 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.4821. Min Act: -0.0000

Data Index: 1338110 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.3548. Min Act: -0.0000

Data Index: 825776 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.5307. Min Act: -0.0000

Data Index: 1300458 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.1998. Min Act: -0.0000

Data Index: 503178 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.1294. Min Act: -0.0000

Data Index: 1083767 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.2473. Min Act: -0.0000

Data Index: 750203 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 2.6237. Min Range: -2.6237

Max Act: 1.9722. Min Act: -0.0000

Data Index: 507518 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.3397. Min Act: -0.0000

Data Index: 123121 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.2252. Min Act: -0.0000

Data Index: 655617 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.1702. Min Act: -0.0000

Data Index: 942913 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.2020. Min Act: -0.0000

Data Index: 654693 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.4005. Min Act: -0.0000

Data Index: 1221974 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.2117. Min Act: -0.0000

Data Index: 588797 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.1602. Min Act: -0.0000

Data Index: 281709 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 2.6237. Min Range: -2.6237

Max Act: 2.3042. Min Act: -0.0000

Data Index: 1293337 (C4 (Web Text))

Max Activating Token Index: 328