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

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

Neuron 1451 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1444108 (Python Code)

Max Activating Token Index: 837

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1423259 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1512810 (Python Code)

Max Activating Token Index: 605

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1376847 (Python Code)

Max Activating Token Index: 480

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1393577 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0817. Min Act: -0.0001

Data Index: 597736 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1442148 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1623520 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1469762 (Python Code)

Max Activating Token Index: 559

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1457640 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1568843 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0816. Min Act: -0.0000

Data Index: 415513 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1622017 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1401694 (Python Code)

Max Activating Token Index: 34

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1650018 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1515649 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1447592 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1471255 (Python Code)

Max Activating Token Index: 913

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1376412 (Python Code)

Max Activating Token Index: 752

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1489247 (Python Code)

Max Activating Token Index: 328