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

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

Neuron 4609 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3573. Min Range: -2.3573

Max Act: 2.3573. Min Act: -0.0001

Data Index: 1434934 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 2.3573. Min Range: -2.3573

Max Act: 2.2236. Min Act: -0.0001

Data Index: 1490691 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.9941. Min Act: -0.0000

Data Index: 1559887 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.4689. Min Act: -0.0000

Data Index: 1635801 (Python Code)

Max Activating Token Index: 257

Text #4

Max Range: 2.3573. Min Range: -2.3573

Max Act: 2.1792. Min Act: -0.0000

Data Index: 1427587 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.8566. Min Act: -0.0000

Data Index: 1654169 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1571061 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.9775. Min Act: -0.0001

Data Index: 1654687 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.8524. Min Act: -0.0000

Data Index: 1456713 (Python Code)

Max Activating Token Index: 56

Text #9

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.8014. Min Act: -0.0001

Data Index: 1458049 (Python Code)

Max Activating Token Index: 35

Text #10

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.8081. Min Act: -0.0000

Data Index: 1605887 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.8000. Min Act: -0.0000

Data Index: 1437978 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 2.3573. Min Range: -2.3573

Max Act: 2.0694. Min Act: -0.0000

Data Index: 1606400 (Python Code)

Max Activating Token Index: 345

Text #13

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.8117. Min Act: -0.0001

Data Index: 1458138 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.9195. Min Act: -0.0000

Data Index: 1390302 (Python Code)

Max Activating Token Index: 17

Text #15

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1485217 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1379881 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.5801. Min Act: -0.0000

Data Index: 1530954 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.6399. Min Act: -0.0001

Data Index: 1644350 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 2.3573. Min Range: -2.3573

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1443047 (Python Code)

Max Activating Token Index: 509