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

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

Neuron 69 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2466. Min Act: -0.1700

Data Index: 1610082 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2779. Min Act: -0.1700

Data Index: 1585110 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2466. Min Act: -0.1700

Data Index: 1415908 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 1626017 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 1473613 (Python Code)

Max Activating Token Index: 34

Text #5

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2466. Min Act: -0.1700

Data Index: 1468979 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2779. Min Act: -0.1700

Data Index: 1590609 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2466. Min Act: -0.1700

Data Index: 1501960 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2466. Min Act: -0.1700

Data Index: 1415784 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.1841. Min Act: -0.1700

Data Index: 126060 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.1841. Min Act: -0.1700

Data Index: 1524708 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 1397422 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 1470158 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2466. Min Act: -0.1700

Data Index: 1597010 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.1841. Min Act: -0.1700

Data Index: 1542824 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 1653013 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 1567465 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 1512169 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.2154. Min Act: -0.1700

Data Index: 559918 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 4.2779. Min Range: -4.2779

Max Act: 4.1841. Min Act: -0.1700

Data Index: 1611431 (Python Code)

Max Activating Token Index: 49