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

Dataset: Open Web Text

Neuron 2548 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: 4.8320. Min Range: -4.8320

Max Act: 4.8320. Min Act: -0.1700

Data Index: 6781927 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 8582820 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 3649597 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 727421 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 6551415 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 6123611 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 5189418 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.8008. Min Act: -0.1700

Data Index: 5177669 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 7309423 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 7281191 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 3290420 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 7145771 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 178975 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 909591 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 4602498 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 4525706 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 1942248 (Open Web Text)

Max Activating Token Index: 161

Text #17

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 4218993 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 1886244 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 4.8320. Min Range: -4.8320

Max Act: 4.7695. Min Act: -0.1700

Data Index: 1703539 (Open Web Text)

Max Activating Token Index: 1023