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

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

Neuron 767 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: 0.1076. Min Range: -0.1076

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1581542 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1500989 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1508725 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1430423 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1369370 (Python Code)

Max Activating Token Index: 984

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1639500 (Python Code)

Max Activating Token Index: 149

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1614824 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1385286 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1360317 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1469296 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1399759 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1377026 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1496947 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1499004 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1597787 (Python Code)

Max Activating Token Index: 849

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0936. Min Act: -0.0001

Data Index: 37414 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1575743 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1481063 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1561626 (Python Code)

Max Activating Token Index: 407

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1450150 (Python Code)

Max Activating Token Index: 290