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

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

Neuron 4451 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: 0.7588. Min Range: -0.7588

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1146590 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5556. Min Act: -0.0000

Data Index: 213656 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5378. Min Act: -0.0000

Data Index: 254995 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5449. Min Act: -0.0000

Data Index: 145869 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5346. Min Act: -0.0000

Data Index: 202936 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1191759 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.5863. Min Act: -0.0000

Data Index: 952484 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4715. Min Act: -0.0000

Data Index: 473166 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4794. Min Act: -0.0000

Data Index: 518961 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4876. Min Act: -0.0000

Data Index: 702874 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1073788 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4706. Min Act: -0.0000

Data Index: 650555 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1074276 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1294223 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4107. Min Act: -0.0000

Data Index: 765102 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4667. Min Act: -0.0000

Data Index: 162868 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1318069 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4214. Min Act: -0.0000

Data Index: 988906 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1273370 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.7588. Min Range: -0.7588

Max Act: 0.4215. Min Act: -0.0000

Data Index: 358053 (C4 (Web Text))

Max Activating Token Index: 202