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

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

Neuron 1987 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8371. Min Act: -0.1700

Data Index: 1542478 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8527. Min Act: -0.1700

Data Index: 1529377 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8214. Min Act: -0.1700

Data Index: 1545190 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7901. Min Act: -0.1700

Data Index: 1581617 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7745. Min Act: -0.1700

Data Index: 1508087 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7119. Min Act: -0.1700

Data Index: 1642345 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7119. Min Act: -0.1700

Data Index: 1556206 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7276. Min Act: -0.1700

Data Index: 1512080 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1458884 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7119. Min Act: -0.1700

Data Index: 1471806 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1479893 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1409446 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1561969 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1638611 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1610759 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1532927 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6650. Min Act: -0.1700

Data Index: 1407447 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1608545 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6963. Min Act: -0.1700

Data Index: 1507923 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1633329 (Python Code)

Max Activating Token Index: 13