Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 610 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1515953 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6601. Min Act: -0.1700

Data Index: 1647897 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6601. Min Act: -0.1700

Data Index: 20970 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6287. Min Act: -0.1700

Data Index: 1577996 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6287. Min Act: -0.1700

Data Index: 1396746 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1608850 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1636392 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6131. Min Act: -0.1700

Data Index: 1573774 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1450026 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.6131. Min Act: -0.1700

Data Index: 1465245 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1474817 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1409817 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1650493 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1491069 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1447417 (Python Code)

Max Activating Token Index: 45

Text #15

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1590195 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1589970 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1554015 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1589067 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 3.6914. Min Range: -3.6914

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1454293 (Python Code)

Max Activating Token Index: 21