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

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

Neuron 3065 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2868. Min Range: -1.2868

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1526972 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 1.2868. Min Range: -1.2868

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1582891 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 1.2868. Min Range: -1.2868

Max Act: 1.0862. Min Act: -0.0000

Data Index: 969351 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1529668 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 1.2868. Min Range: -1.2868

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1575539 (Python Code)

Max Activating Token Index: 1006

Text #5

Max Range: 1.2868. Min Range: -1.2868

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1496950 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1430698 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 1.2868. Min Range: -1.2868

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1610673 (Python Code)

Max Activating Token Index: 796

Text #8

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1418625 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1561006 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1370576 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8335. Min Act: -0.0000

Data Index: 893125 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1484250 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1574050 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1452393 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1440560 (Python Code)

Max Activating Token Index: 184

Text #16

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1484021 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1403991 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1459849 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 1.2868. Min Range: -1.2868

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1383377 (Python Code)

Max Activating Token Index: 461