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

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

Neuron 4075 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1078916 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0982. Min Act: -0.0001

Data Index: 812995 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1641729 (Python Code)

Max Activating Token Index: 89

Text #3

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1436881 (Python Code)

Max Activating Token Index: 972

Text #4

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0904. Min Act: -0.0001

Data Index: 375992 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1464666 (Python Code)

Max Activating Token Index: 863

Text #6

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1582438 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1591279 (Python Code)

Max Activating Token Index: 842

Text #8

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1462045 (Python Code)

Max Activating Token Index: 576

Text #9

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1385036 (Python Code)

Max Activating Token Index: 974

Text #10

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1369096 (Python Code)

Max Activating Token Index: 286

Text #11

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0795. Min Act: -0.0001

Data Index: 803310 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1405201 (Python Code)

Max Activating Token Index: 481

Text #13

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1420277 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1429424 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0815. Min Act: -0.0001

Data Index: 300732 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0743. Min Act: -0.0001

Data Index: 417064 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0742. Min Act: -0.0001

Data Index: 773550 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1385436 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 0.1057. Min Range: -0.1057

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1587103 (Python Code)

Max Activating Token Index: 924