Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 529 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.8216. Min Act: -0.1700

Data Index: 6676589 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7813. Min Act: -0.1700

Data Index: 4869367 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7754. Min Act: -0.1700

Data Index: 7727678 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7519. Min Act: -0.1700

Data Index: 7389628 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7579. Min Act: -0.1700

Data Index: 4985588 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7462. Min Act: -0.1700

Data Index: 6655985 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7290. Min Act: -0.1700

Data Index: 6905758 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7218. Min Act: -0.1700

Data Index: 8654989 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7222. Min Act: -0.1700

Data Index: 2141261 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7187. Min Act: -0.1700

Data Index: 6289056 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7266. Min Act: -0.1700

Data Index: 182374 (Open Web Text)

Max Activating Token Index: 868

Text #11

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7062. Min Act: -0.1700

Data Index: 820173 (Open Web Text)

Max Activating Token Index: 93

Text #12

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7142. Min Act: -0.1700

Data Index: 1583896 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.7006. Min Act: -0.1700

Data Index: 6768467 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.6960. Min Act: -0.1700

Data Index: 5758523 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.6987. Min Act: -0.1700

Data Index: 6890164 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.6957. Min Act: -0.1700

Data Index: 2147857 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.6876. Min Act: -0.1700

Data Index: 7457790 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.6849. Min Act: -0.1700

Data Index: 6238756 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.8216. Min Range: -2.8216

Max Act: 2.6829. Min Act: -0.1700

Data Index: 7943834 (Open Web Text)

Max Activating Token Index: 4