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

Dataset: Open Web Text

Neuron 394 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: 4.6240. Min Range: -4.6240

Max Act: 4.6240. Min Act: -0.1700

Data Index: 1364760 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5741. Min Act: -0.1700

Data Index: 1296128 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.6046. Min Act: -0.1700

Data Index: 3378622 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5691. Min Act: -0.1700

Data Index: 1130023 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5602. Min Act: -0.1700

Data Index: 3645566 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5115. Min Act: -0.1700

Data Index: 1709908 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5277. Min Act: -0.1700

Data Index: 5363974 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4827. Min Act: -0.1700

Data Index: 8300223 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5023. Min Act: -0.1699

Data Index: 1127953 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5000. Min Act: -0.1700

Data Index: 7658849 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4926. Min Act: -0.1700

Data Index: 7549221 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4830. Min Act: -0.1700

Data Index: 3405649 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4844. Min Act: -0.1700

Data Index: 6598017 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5010. Min Act: -0.1700

Data Index: 8779358 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.5094. Min Act: -0.1700

Data Index: 8588392 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4629. Min Act: -0.1700

Data Index: 6857272 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4690. Min Act: -0.1700

Data Index: 6594560 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4465. Min Act: -0.1700

Data Index: 6012376 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4726. Min Act: -0.1700

Data Index: 1905829 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.6240. Min Range: -4.6240

Max Act: 4.4437. Min Act: -0.1700

Data Index: 1617794 (Open Web Text)

Max Activating Token Index: 13