Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3433 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2196. Min Range: -1.2196

Max Act: 1.2196. Min Act: -0.0000

Data Index: 1654666 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 1.2196. Min Range: -1.2196

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1468168 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1631701 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1645587 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 1.2196. Min Range: -1.2196

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1502014 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9740. Min Act: -0.0000

Data Index: 1625116 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1628888 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1418706 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.9147. Min Act: -0.0000

Data Index: 1625160 (Python Code)

Max Activating Token Index: 269

Text #9

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1645519 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1567094 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1569509 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1373408 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1546246 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1434024 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1473935 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1426823 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1522496 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1413313 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 1.2196. Min Range: -1.2196

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1622331 (Python Code)

Max Activating Token Index: 500