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

Dataset: Open Web Text

Neuron 1295 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: 3.1468. Min Range: -3.1468

Max Act: 3.1468. Min Act: -0.1700

Data Index: 2164122 (Open Web Text)

Max Activating Token Index: 854

Text #1

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1346. Min Act: -0.1700

Data Index: 3132468 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1253. Min Act: -0.1700

Data Index: 8328600 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1205. Min Act: -0.1700

Data Index: 7840033 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1161. Min Act: -0.1700

Data Index: 4367261 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0986. Min Act: -0.1700

Data Index: 2582938 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1054. Min Act: -0.1700

Data Index: 1796768 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0977. Min Act: -0.1700

Data Index: 7329814 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1076. Min Act: -0.1700

Data Index: 7016508 (Open Web Text)

Max Activating Token Index: 15

Text #9

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1111. Min Act: -0.1700

Data Index: 3213781 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1011. Min Act: -0.1700

Data Index: 1429960 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.1025. Min Act: -0.1700

Data Index: 6113725 (Open Web Text)

Max Activating Token Index: 31

Text #12

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0782. Min Act: -0.1700

Data Index: 6525402 (Open Web Text)

Max Activating Token Index: 807

Text #13

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0901. Min Act: -0.1700

Data Index: 5429403 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0893. Min Act: -0.1700

Data Index: 7781907 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0911. Min Act: -0.1700

Data Index: 5899859 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0995. Min Act: -0.1700

Data Index: 529323 (Open Web Text)

Max Activating Token Index: 708

Text #17

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0798. Min Act: -0.1700

Data Index: 2995596 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0824. Min Act: -0.1700

Data Index: 3091622 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.1468. Min Range: -3.1468

Max Act: 3.0952. Min Act: -0.1700

Data Index: 1867918 (Open Web Text)

Max Activating Token Index: 5