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

Dataset: Open Web Text

Neuron 339 in Layer 2

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: 4.7664. Min Range: -4.7664

Max Act: 4.7664. Min Act: -0.1700

Data Index: 4538595 (Open Web Text)

Max Activating Token Index: 443

Text #1

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7284. Min Act: -0.1700

Data Index: 6875431 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7208. Min Act: -0.1700

Data Index: 1039214 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7141. Min Act: -0.1700

Data Index: 8218531 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7106. Min Act: -0.1700

Data Index: 7334896 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7266. Min Act: -0.1700

Data Index: 3846066 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7242. Min Act: -0.1700

Data Index: 7109716 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.6997. Min Act: -0.1700

Data Index: 7023624 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7196. Min Act: -0.1700

Data Index: 7004977 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7085. Min Act: -0.1700

Data Index: 1847338 (Open Web Text)

Max Activating Token Index: 293

Text #10

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7183. Min Act: -0.1700

Data Index: 2992452 (Open Web Text)

Max Activating Token Index: 234

Text #11

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7160. Min Act: -0.1700

Data Index: 2640487 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.6720. Min Act: -0.1700

Data Index: 6862639 (Open Web Text)

Max Activating Token Index: 798

Text #13

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.6962. Min Act: -0.1700

Data Index: 5286756 (Open Web Text)

Max Activating Token Index: 280

Text #14

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7017. Min Act: -0.1700

Data Index: 5195859 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7025. Min Act: -0.1700

Data Index: 4091302 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.7118. Min Act: -0.1700

Data Index: 7551759 (Open Web Text)

Max Activating Token Index: 254

Text #17

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.6846. Min Act: -0.1700

Data Index: 8126671 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.6691. Min Act: -0.1700

Data Index: 2372306 (Open Web Text)

Max Activating Token Index: 263

Text #19

Max Range: 4.7664. Min Range: -4.7664

Max Act: 4.6918. Min Act: -0.1700

Data Index: 8378246 (Open Web Text)

Max Activating Token Index: 40