Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1068 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1470997 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1496398 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0819. Min Act: -0.0001

Data Index: 877378 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1644635 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0847. Min Act: -0.0001

Data Index: 636087 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0847. Min Act: -0.0001

Data Index: 225850 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1440106 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1544838 (Python Code)

Max Activating Token Index: 990

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1637919 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1410425 (Python Code)

Max Activating Token Index: 245

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0723. Min Act: -0.0001

Data Index: 424663 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0723. Min Act: -0.0001

Data Index: 171437 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0723. Min Act: -0.0001

Data Index: 843874 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1584469 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1423421 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1611553 (Python Code)

Max Activating Token Index: 790

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1414324 (Python Code)

Max Activating Token Index: 721

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0652. Min Act: -0.0001

Data Index: 803504 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1386637 (Python Code)

Max Activating Token Index: 613

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1622445 (Python Code)

Max Activating Token Index: 635