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

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

Neuron 1545 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1640743 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1595491 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1404417 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1364593 (Python Code)

Max Activating Token Index: 776

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1567639 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2268. Min Act: -0.0001

Data Index: 1604729 (Python Code)

Max Activating Token Index: 581

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1568429 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1360125 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1414497 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1569448 (Python Code)

Max Activating Token Index: 499

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1755. Min Act: -0.0001

Data Index: 562522 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1374647 (Python Code)

Max Activating Token Index: 270

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1477562 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1630900 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1534245 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1688. Min Act: -0.0001

Data Index: 1466145 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1598931 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1364294 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1443849 (Python Code)

Max Activating Token Index: 270

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1531571 (Python Code)

Max Activating Token Index: 815