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

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

Neuron 3358 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.1266. Min Act: -0.0001

Data Index: 181780 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9848. Min Act: -0.0001

Data Index: 909155 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0414. Min Act: -0.0001

Data Index: 558083 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0264. Min Act: -0.0001

Data Index: 115688 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0007. Min Act: -0.0001

Data Index: 259162 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0563. Min Act: -0.0001

Data Index: 156536 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0341. Min Act: -0.0001

Data Index: 1082338 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0243. Min Act: -0.0001

Data Index: 292682 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9998. Min Act: -0.0001

Data Index: 100767 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9914. Min Act: -0.0001

Data Index: 304172 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9608. Min Act: -0.0001

Data Index: 1119548 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0484. Min Act: -0.0001

Data Index: 1197225 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9616. Min Act: -0.0001

Data Index: 1346370 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9899. Min Act: -0.0001

Data Index: 1149717 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0167. Min Act: -0.0001

Data Index: 318934 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9819. Min Act: -0.0001

Data Index: 1295909 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9723. Min Act: -0.0001

Data Index: 944810 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 1.1266. Min Range: -1.1266

Max Act: 1.0012. Min Act: -0.0001

Data Index: 355681 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9161. Min Act: -0.0001

Data Index: 89305 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9449. Min Act: -0.0001

Data Index: 479302 (C4 (Web Text))

Max Activating Token Index: 277