Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1080. Min Act: -0.0005

Data Index: 1506468 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1042. Min Act: -0.0005

Data Index: 1542118 (Python Code)

Max Activating Token Index: 117

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1040. Min Act: -0.0005

Data Index: 1438876 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1072. Min Act: -0.0005

Data Index: 1364780 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1053. Min Act: -0.0005

Data Index: 1600636 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1015. Min Act: -0.0005

Data Index: 1625937 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1024. Min Act: -0.0005

Data Index: 1490831 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0005

Data Index: 1439861 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1036. Min Act: -0.0005

Data Index: 1401872 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1019. Min Act: -0.0005

Data Index: 1479585 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0996. Min Act: -0.0005

Data Index: 1381792 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1069. Min Act: -0.0005

Data Index: 1455844 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1017. Min Act: -0.0005

Data Index: 1431245 (Python Code)

Max Activating Token Index: 416

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1029. Min Act: -0.0005

Data Index: 1455331 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1048. Min Act: -0.0005

Data Index: 1535569 (Python Code)

Max Activating Token Index: 468

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1025. Min Act: -0.0005

Data Index: 1443814 (Python Code)

Max Activating Token Index: 911

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1039. Min Act: -0.0005

Data Index: 1461816 (Python Code)

Max Activating Token Index: 655

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1013. Min Act: -0.0005

Data Index: 1609630 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1043. Min Act: -0.0005

Data Index: 1500595 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0992. Min Act: -0.0005

Data Index: 1638037 (Python Code)

Max Activating Token Index: 282