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

Dataset: Open Web Text

Neuron 2292 in Layer 3

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: 3.4502. Min Range: -3.4502

Max Act: 3.4502. Min Act: -0.1700

Data Index: 6112965 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.2248. Min Act: -0.1700

Data Index: 2074149 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.1525. Min Act: -0.1700

Data Index: 7949484 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.1159. Min Act: -0.1700

Data Index: 6408007 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.1165. Min Act: -0.1700

Data Index: 5813778 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.1159. Min Act: -0.1700

Data Index: 7802281 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.1000. Min Act: -0.1700

Data Index: 3639995 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.1056. Min Act: -0.1700

Data Index: 1259423 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0976. Min Act: -0.1700

Data Index: 5195345 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0791. Min Act: -0.1700

Data Index: 2055353 (Open Web Text)

Max Activating Token Index: 738

Text #10

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0782. Min Act: -0.1700

Data Index: 5280533 (Open Web Text)

Max Activating Token Index: 409

Text #11

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0958. Min Act: -0.1700

Data Index: 3419899 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0958. Min Act: -0.1700

Data Index: 8742537 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0813. Min Act: -0.1700

Data Index: 605012 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0958. Min Act: -0.1700

Data Index: 943151 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0759. Min Act: -0.1700

Data Index: 8381553 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0719. Min Act: -0.1700

Data Index: 281234 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0670. Min Act: -0.1700

Data Index: 8826536 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0640. Min Act: -0.1700

Data Index: 2628041 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.0728. Min Act: -0.1700

Data Index: 8355867 (Open Web Text)

Max Activating Token Index: 37