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

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

Neuron 1656 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.4781. Min Act: -0.0001

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.4602. Min Act: -0.0001

Data Index: 773201 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.5000. Min Act: -0.0001

Data Index: 70256 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.1978. Min Act: -0.0001

Data Index: 809892 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.3544. Min Act: -0.0001

Data Index: 910981 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.3220. Min Act: -0.0001

Data Index: 658663 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.1501. Min Act: -0.0001

Data Index: 224426 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.0220. Min Act: -0.0001

Data Index: 1046619 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.7731. Min Act: -0.0001

Data Index: 1129716 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.8704. Min Act: -0.0001

Data Index: 252752 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.9765. Min Act: -0.0001

Data Index: 941946 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.8322. Min Act: -0.0001

Data Index: 1090771 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.9646. Min Act: -0.0001

Data Index: 720338 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.9182. Min Act: -0.0001

Data Index: 904293 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 3.5000. Min Range: -3.5000

Max Act: 3.0303. Min Act: -0.0001

Data Index: 995838 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.8879. Min Act: -0.0001

Data Index: 381463 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.7043. Min Act: -0.0001

Data Index: 949844 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.6891. Min Act: -0.0001

Data Index: 449412 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.6551. Min Act: -0.0001

Data Index: 1068092 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 3.5000. Min Range: -3.5000

Max Act: 2.7764. Min Act: -0.0001

Data Index: 744406 (C4 (Web Text))

Max Activating Token Index: 123