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

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

Neuron 1399 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.2766. Min Act: -0.1700

Data Index: 1466403 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.2766. Min Act: -0.1700

Data Index: 1390792 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1823. Min Act: -0.1700

Data Index: 1374041 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1980. Min Act: -0.1700

Data Index: 1537920 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1350. Min Act: -0.1700

Data Index: 1581276 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1665. Min Act: -0.1700

Data Index: 1480687 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1823. Min Act: -0.1700

Data Index: 1424840 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1035. Min Act: -0.1700

Data Index: 1369863 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1035. Min Act: -0.1700

Data Index: 1570989 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1193. Min Act: -0.1700

Data Index: 1455790 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1193. Min Act: -0.1700

Data Index: 1525081 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1193. Min Act: -0.1700

Data Index: 1414503 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.0877. Min Act: -0.1700

Data Index: 1411282 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.0562. Min Act: -0.1700

Data Index: 1463053 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.0720. Min Act: -0.1700

Data Index: 1547358 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.1193. Min Act: -0.1700

Data Index: 1537988 (Python Code)

Max Activating Token Index: 743

Text #16

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.0246. Min Act: -0.1700

Data Index: 1648100 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.0877. Min Act: -0.1700

Data Index: 1450585 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.0720. Min Act: -0.1700

Data Index: 1567991 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.2766. Min Range: -3.2766

Max Act: 3.0720. Min Act: -0.1700

Data Index: 1488188 (Python Code)

Max Activating Token Index: 444