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

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

Neuron 1109 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1441235 (Python Code)

Max Activating Token Index: 429

Text #1

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.9644. Min Act: -0.0000

Data Index: 1067422 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1430804 (Python Code)

Max Activating Token Index: 630

Text #3

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1594563 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.9071. Min Act: -0.0000

Data Index: 484895 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1518332 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1540972 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1391534 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1597914 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1527963 (Python Code)

Max Activating Token Index: 596

Text #10

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1639012 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1646821 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7964. Min Act: -0.0000

Data Index: 557010 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1493033 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1404713 (Python Code)

Max Activating Token Index: 482

Text #15

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1384809 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1518936 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1453780 (Python Code)

Max Activating Token Index: 548

Text #18

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1519030 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1614491 (Python Code)

Max Activating Token Index: 683