Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2817 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.7722. Min Act: -0.0001

Data Index: 1414131 (Python Code)

Max Activating Token Index: 535

Text #1

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.7594. Min Act: -0.0001

Data Index: 1498173 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1445628 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.6745. Min Act: -0.0001

Data Index: 1653773 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.7071. Min Act: -0.0001

Data Index: 1365747 (Python Code)

Max Activating Token Index: 511

Text #5

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.6911. Min Act: -0.0001

Data Index: 1370467 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.6398. Min Act: -0.0001

Data Index: 1564168 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.6260. Min Act: -0.0001

Data Index: 1567904 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.6034. Min Act: -0.0001

Data Index: 1439066 (Python Code)

Max Activating Token Index: 111

Text #9

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1374142 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1401915 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.6085. Min Act: -0.0001

Data Index: 1359954 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1401178 (Python Code)

Max Activating Token Index: 490

Text #13

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5675. Min Act: -0.0001

Data Index: 1362874 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5791. Min Act: -0.0001

Data Index: 1536723 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5991. Min Act: -0.0001

Data Index: 1584564 (Python Code)

Max Activating Token Index: 51

Text #16

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5715. Min Act: -0.0001

Data Index: 1506311 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5616. Min Act: -0.0001

Data Index: 1601356 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5589. Min Act: -0.0001

Data Index: 1571129 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.7794. Min Range: -0.7794

Max Act: 0.5041. Min Act: -0.0001

Data Index: 1435734 (Python Code)

Max Activating Token Index: 971