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

Dataset: Open Web Text

Neuron 680 in Layer 1

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: 4.6511. Min Range: -4.6511

Max Act: 4.6511. Min Act: -0.1700

Data Index: 2967000 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6511. Min Act: -0.1700

Data Index: 3996186 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6511. Min Act: -0.1700

Data Index: 1268495 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6511. Min Act: -0.1700

Data Index: 4884457 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6398. Min Act: -0.1700

Data Index: 7736362 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6398. Min Act: -0.1700

Data Index: 1869285 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6398. Min Act: -0.1700

Data Index: 4586540 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6285. Min Act: -0.1700

Data Index: 8351197 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6251. Min Act: -0.1700

Data Index: 5719569 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6200. Min Act: -0.1700

Data Index: 4993451 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.5966. Min Act: -0.1700

Data Index: 8752632 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6015. Min Act: -0.1700

Data Index: 4884451 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6073. Min Act: -0.1700

Data Index: 4821120 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6251. Min Act: -0.1700

Data Index: 1869288 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6251. Min Act: -0.1700

Data Index: 4436093 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6186. Min Act: -0.1700

Data Index: 303616 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6015. Min Act: -0.1700

Data Index: 7046022 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.6311. Min Act: -0.1700

Data Index: 6398800 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.5966. Min Act: -0.1700

Data Index: 459298 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.6511. Min Range: -4.6511

Max Act: 4.5756. Min Act: -0.1700

Data Index: 2934711 (Open Web Text)

Max Activating Token Index: 10