Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 378 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.1024. Min Act: -0.1700

Data Index: 63030 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.1024. Min Act: -0.1700

Data Index: 910012 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.1024. Min Act: -0.1700

Data Index: 4152539 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0867. Min Act: -0.1700

Data Index: 1398261 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0709. Min Act: -0.1700

Data Index: 3445721 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0709. Min Act: -0.1700

Data Index: 2511912 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0551. Min Act: -0.1700

Data Index: 2060807 (Open Web Text)

Max Activating Token Index: 25

Text #7

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0551. Min Act: -0.1700

Data Index: 1202554 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 3045950 (Open Web Text)

Max Activating Token Index: 26

Text #9

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 3223528 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 4517897 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 2038200 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 3328042 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 6120892 (Open Web Text)

Max Activating Token Index: 116

Text #14

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0235. Min Act: -0.1700

Data Index: 6701923 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 7458108 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 8594552 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0235. Min Act: -0.1700

Data Index: 8677174 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 1287152 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.1024. Min Range: -3.1024

Max Act: 3.0393. Min Act: -0.1700

Data Index: 1351715 (Open Web Text)

Max Activating Token Index: 45