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

Dataset: Open Web Text

Neuron 1963 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: 1.5851. Min Range: -1.5851

Max Act: 1.5787. Min Act: -0.1700

Data Index: 1668910 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5851. Min Act: -0.1699

Data Index: 4861489 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5719. Min Act: -0.1699

Data Index: 3024692 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5636. Min Act: -0.1689

Data Index: 8658190 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5636. Min Act: -0.1700

Data Index: 3095129 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5636. Min Act: -0.1700

Data Index: 7336788 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5592. Min Act: -0.1700

Data Index: 125710 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5403. Min Act: -0.1700

Data Index: 347184 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5403. Min Act: -0.1700

Data Index: 5070339 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5403. Min Act: -0.1700

Data Index: 5848744 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5385. Min Act: -0.1700

Data Index: 4832856 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5403. Min Act: -0.1700

Data Index: 8332929 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5315. Min Act: -0.1700

Data Index: 1414794 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5270. Min Act: -0.1700

Data Index: 456161 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5253. Min Act: -0.1699

Data Index: 1995596 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5230. Min Act: -0.1700

Data Index: 4756914 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5195. Min Act: -0.1700

Data Index: 1255012 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5210. Min Act: -0.1700

Data Index: 7889425 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5207. Min Act: -0.1700

Data Index: 1826283 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 1.5851. Min Range: -1.5851

Max Act: 1.5225. Min Act: -0.1700

Data Index: 1899606 (Open Web Text)

Max Activating Token Index: 6