Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3641 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.3744. Min Act: -0.0000

Data Index: 1547309 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.5441. Min Act: -0.0000

Data Index: 1551792 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.2452. Min Act: -0.0000

Data Index: 1626713 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.2175. Min Act: -0.0000

Data Index: 1561273 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.2163. Min Act: -0.0000

Data Index: 1523589 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.2212. Min Act: -0.0000

Data Index: 1432021 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.1031. Min Act: -0.0000

Data Index: 1513074 (Python Code)

Max Activating Token Index: 17

Text #7

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.9637. Min Act: -0.0000

Data Index: 1643932 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.2201. Min Act: -0.0000

Data Index: 1458696 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 3.5441. Min Range: -3.5441

Max Act: 3.1201. Min Act: -0.0001

Data Index: 1584768 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.9584. Min Act: -0.0000

Data Index: 1457739 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.9608. Min Act: -0.0000

Data Index: 1534306 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.9507. Min Act: -0.0000

Data Index: 1469376 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.9052. Min Act: -0.0000

Data Index: 1610694 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.8831. Min Act: -0.0000

Data Index: 1562790 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.8316. Min Act: -0.0000

Data Index: 1437146 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.8071. Min Act: -0.0000

Data Index: 1515171 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.7955. Min Act: -0.0000

Data Index: 1518123 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.7877. Min Act: -0.0000

Data Index: 1409882 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 3.5441. Min Range: -3.5441

Max Act: 2.7812. Min Act: -0.0000

Data Index: 1477004 (Python Code)

Max Activating Token Index: 82