Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5999 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0831. Min Act: -0.0001

Data Index: 138330 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0816. Min Act: -0.0001

Data Index: 305296 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0001

Data Index: 34819 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1107017 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0748. Min Act: -0.0001

Data Index: 345880 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0558. Min Act: -0.0001

Data Index: 111173 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1341970 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0779. Min Act: -0.0001

Data Index: 820517 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0649. Min Act: -0.0001

Data Index: 775599 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1032527 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0751. Min Act: -0.0001

Data Index: 499025 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0740. Min Act: -0.0001

Data Index: 993168 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0683. Min Act: -0.0001

Data Index: 648020 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1328506 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0736. Min Act: -0.0001

Data Index: 811425 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1352187 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1301584 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0615. Min Act: -0.0001

Data Index: 561455 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0616. Min Act: -0.0001

Data Index: 574472 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0682. Min Act: -0.0001

Data Index: 719509 (C4 (Web Text))

Max Activating Token Index: 83