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

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

Neuron 3464 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5078. Min Range: -2.5078

Max Act: 2.5078. Min Act: -0.0000

Data Index: 1398385 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 2.5078. Min Range: -2.5078

Max Act: 2.3000. Min Act: -0.0000

Data Index: 1395177 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 2.5078. Min Range: -2.5078

Max Act: 2.2726. Min Act: -0.0000

Data Index: 1582060 (Python Code)

Max Activating Token Index: 455

Text #3

Max Range: 2.5078. Min Range: -2.5078

Max Act: 2.2110. Min Act: -0.0000

Data Index: 1373134 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 2.5078. Min Range: -2.5078

Max Act: 2.1040. Min Act: -0.0000

Data Index: 1649125 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 2.5078. Min Range: -2.5078

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1442117 (Python Code)

Max Activating Token Index: 995

Text #6

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1560616 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7873. Min Act: 0.0000

Data Index: 1584406 (Python Code)

Max Activating Token Index: 302

Text #8

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.6644. Min Act: -0.0000

Data Index: 1652503 (Python Code)

Max Activating Token Index: 523

Text #9

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.9599. Min Act: -0.0000

Data Index: 1364181 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7307. Min Act: 0.0000

Data Index: 1369193 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7313. Min Act: -0.0000

Data Index: 1585712 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7329. Min Act: 0.0000

Data Index: 1501340 (Python Code)

Max Activating Token Index: 484

Text #13

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7313. Min Act: 0.0000

Data Index: 1604668 (Python Code)

Max Activating Token Index: 476

Text #14

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7123. Min Act: -0.0000

Data Index: 1455936 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1469594 (Python Code)

Max Activating Token Index: 986

Text #16

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1413084 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.6843. Min Act: -0.0000

Data Index: 1368955 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.5256. Min Act: 0.0000

Data Index: 1482244 (Python Code)

Max Activating Token Index: 943

Text #19

Max Range: 2.5078. Min Range: -2.5078

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1411309 (Python Code)

Max Activating Token Index: 943