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

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

Neuron 1882 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5512. Min Act: -0.1700

Data Index: 1531497 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5512. Min Act: -0.1700

Data Index: 1406961 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5424. Min Act: -0.1700

Data Index: 1366306 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5161. Min Act: -0.1700

Data Index: 1429044 (Python Code)

Max Activating Token Index: 11

Text #4

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5161. Min Act: -0.1700

Data Index: 1645356 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5161. Min Act: -0.1700

Data Index: 1434009 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5161. Min Act: -0.1700

Data Index: 1551377 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5161. Min Act: -0.1700

Data Index: 1414499 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5161. Min Act: -0.1700

Data Index: 1643896 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5074. Min Act: -0.1700

Data Index: 1550437 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4986. Min Act: -0.1700

Data Index: 1418224 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4986. Min Act: -0.1700

Data Index: 1563880 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.5074. Min Act: -0.1700

Data Index: 1496370 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4898. Min Act: -0.1700

Data Index: 1568499 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4986. Min Act: -0.1700

Data Index: 1499350 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4986. Min Act: -0.1700

Data Index: 1626514 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4810. Min Act: -0.1700

Data Index: 1604671 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4986. Min Act: -0.1700

Data Index: 1584769 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4986. Min Act: -0.1700

Data Index: 1581168 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 1.5512. Min Range: -1.5512

Max Act: 1.4986. Min Act: -0.1700

Data Index: 1465959 (Python Code)

Max Activating Token Index: 8