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

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

Neuron 149 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: 0.2828. Min Range: -0.2828

Max Act: 0.2828. Min Act: -0.0004

Data Index: 1536359 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2700. Min Act: -0.0004

Data Index: 1640772 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2660. Min Act: -0.0004

Data Index: 1462667 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2604. Min Act: -0.0004

Data Index: 1572397 (Python Code)

Max Activating Token Index: 28

Text #4

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2778. Min Act: -0.0004

Data Index: 1473394 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2653. Min Act: -0.0004

Data Index: 1487751 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2565. Min Act: -0.0004

Data Index: 1645929 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2646. Min Act: -0.0004

Data Index: 1650166 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2646. Min Act: -0.0004

Data Index: 1521265 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2650. Min Act: -0.0004

Data Index: 1589921 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2562. Min Act: -0.0004

Data Index: 1595014 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2558. Min Act: -0.0004

Data Index: 1416685 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2727. Min Act: -0.0004

Data Index: 1447826 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2698. Min Act: -0.0004

Data Index: 1570210 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2595. Min Act: -0.0004

Data Index: 1526589 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2511. Min Act: -0.0004

Data Index: 1581812 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2669. Min Act: -0.0004

Data Index: 1469319 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2502. Min Act: -0.0004

Data Index: 1446370 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2674. Min Act: -0.0004

Data Index: 1649117 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 0.2828. Min Range: -0.2828

Max Act: 0.2409. Min Act: -0.0004

Data Index: 1464301 (Python Code)

Max Activating Token Index: 293