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

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

Neuron 2632 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0004

Data Index: 1491346 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0584. Min Act: -0.0004

Data Index: 1367342 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0569. Min Act: -0.0004

Data Index: 1414001 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0569. Min Act: -0.0004

Data Index: 1522040 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0579. Min Act: -0.0004

Data Index: 1557861 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0514. Min Act: -0.0004

Data Index: 1403419 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0511. Min Act: -0.0004

Data Index: 1649218 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0503. Min Act: -0.0004

Data Index: 1547200 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0527. Min Act: -0.0004

Data Index: 1421445 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0545. Min Act: -0.0004

Data Index: 1415747 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0513. Min Act: -0.0004

Data Index: 1537102 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0533. Min Act: -0.0004

Data Index: 1455559 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0532. Min Act: -0.0004

Data Index: 1523663 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1398600 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0499. Min Act: -0.0004

Data Index: 1474827 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0550. Min Act: -0.0004

Data Index: 1529891 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0550. Min Act: -0.0004

Data Index: 1633062 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0509. Min Act: -0.0004

Data Index: 1501532 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0502. Min Act: -0.0004

Data Index: 1524978 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0531. Min Act: -0.0004

Data Index: 1456908 (Python Code)

Max Activating Token Index: 11