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

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

Neuron 809 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.4717. Min Act: -0.0000

Data Index: 298687 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1002385 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.4592. Min Act: -0.0000

Data Index: 809169 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.2360. Min Act: -0.0000

Data Index: 276549 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.2370. Min Act: -0.0000

Data Index: 135883 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1788. Min Act: -0.0000

Data Index: 577476 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1456. Min Act: -0.0000

Data Index: 756801 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1342908 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1859. Min Act: -0.0000

Data Index: 1150081 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1762. Min Act: -0.0000

Data Index: 256144 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1981. Min Act: -0.0000

Data Index: 10757 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1058725 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0637. Min Act: -0.0000

Data Index: 753460 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1358364 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0020. Min Act: -0.0000

Data Index: 123791 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.4717. Min Range: -1.4717

Max Act: 0.9639. Min Act: -0.0000

Data Index: 628520 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0274. Min Act: -0.0000

Data Index: 765579 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0728. Min Act: -0.0000

Data Index: 470035 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1187566 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.4717. Min Range: -1.4717

Max Act: 1.0689. Min Act: -0.0000

Data Index: 1103461 (C4 (Web Text))

Max Activating Token Index: 716