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

Dataset: Open Web Text

Neuron 395 in Layer 4

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: 3.8828. Min Range: -3.8828

Max Act: 3.8828. Min Act: -0.1700

Data Index: 4628224 (Open Web Text)

Max Activating Token Index: 28

Text #1

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8420. Min Act: -0.1700

Data Index: 3536756 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8167. Min Act: -0.1700

Data Index: 6020339 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.8430. Min Act: -0.1700

Data Index: 7770640 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7896. Min Act: -0.1700

Data Index: 6906793 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7329. Min Act: -0.1700

Data Index: 1196504 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7457. Min Act: -0.1700

Data Index: 5708379 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7453. Min Act: -0.1700

Data Index: 3090573 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7247. Min Act: -0.1700

Data Index: 114299 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7138. Min Act: -0.1700

Data Index: 2889616 (Open Web Text)

Max Activating Token Index: 567

Text #10

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7314. Min Act: -0.1700

Data Index: 5063362 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7062. Min Act: -0.1700

Data Index: 4859485 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7130. Min Act: -0.1700

Data Index: 3458335 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7027. Min Act: -0.1700

Data Index: 6991584 (Open Web Text)

Max Activating Token Index: 312

Text #14

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7165. Min Act: -0.1700

Data Index: 5193550 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.7085. Min Act: -0.1700

Data Index: 3492711 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6845. Min Act: -0.1700

Data Index: 6853800 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6845. Min Act: -0.1700

Data Index: 2001714 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6864. Min Act: -0.1700

Data Index: 3469746 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 3.8828. Min Range: -3.8828

Max Act: 3.6804. Min Act: -0.1700

Data Index: 7493637 (Open Web Text)

Max Activating Token Index: 689