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

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

Neuron 1751 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: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1511098 (Python Code)

Max Activating Token Index: 213

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1212666 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0782. Min Act: -0.0001

Data Index: 145278 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0740. Min Act: -0.0001

Data Index: 272382 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0744. Min Act: -0.0001

Data Index: 792113 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1353859 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1102748 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0618. Min Act: -0.0000

Data Index: 130286 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1196416 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1332524 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0640. Min Act: -0.0001

Data Index: 478036 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0621. Min Act: -0.0001

Data Index: 45097 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1409504 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1084439 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0590. Min Act: -0.0000

Data Index: 179087 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1211851 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1319237 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0617. Min Act: -0.0000

Data Index: 859456 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0557. Min Act: -0.0001

Data Index: 751653 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0546. Min Act: -0.0001

Data Index: 88799 (C4 (Web Text))

Max Activating Token Index: 771