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

Dataset: Open Web Text

Neuron 1415 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: 4.1750. Min Range: -4.1750

Max Act: 4.1750. Min Act: -0.1700

Data Index: 8699131 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.1055. Min Act: -0.1700

Data Index: 8482363 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0824. Min Act: -0.1700

Data Index: 1824866 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.1040. Min Act: -0.1700

Data Index: 1548703 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0828. Min Act: -0.1700

Data Index: 4780764 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0608. Min Act: -0.1700

Data Index: 6656611 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0200. Min Act: -0.1700

Data Index: 8264908 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0470. Min Act: -0.1700

Data Index: 7141421 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0378. Min Act: -0.1700

Data Index: 3060184 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0310. Min Act: -0.1700

Data Index: 2761403 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0397. Min Act: -0.1700

Data Index: 316381 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0286. Min Act: -0.1700

Data Index: 1879420 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0351. Min Act: -0.1700

Data Index: 6105448 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0378. Min Act: -0.1700

Data Index: 2151041 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.1750. Min Range: -4.1750

Max Act: 3.9934. Min Act: -0.1700

Data Index: 7139594 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0068. Min Act: -0.1700

Data Index: 1638400 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0188. Min Act: -0.1700

Data Index: 206178 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.1750. Min Range: -4.1750

Max Act: 3.9923. Min Act: -0.1700

Data Index: 6415262 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0109. Min Act: -0.1700

Data Index: 4548874 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.1750. Min Range: -4.1750

Max Act: 4.0042. Min Act: -0.1700

Data Index: 5299251 (Open Web Text)

Max Activating Token Index: 12