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

Dataset: Open Web Text

Neuron 909 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: 1.6501. Min Range: -1.6501

Max Act: 1.6501. Min Act: -0.1698

Data Index: 2360438 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6292. Min Act: -0.1700

Data Index: 1017638 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6258. Min Act: -0.1695

Data Index: 1605403 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6094. Min Act: -0.1695

Data Index: 5361280 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6165. Min Act: -0.1657

Data Index: 968715 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6164. Min Act: -0.1666

Data Index: 7915305 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.6049. Min Act: -0.1700

Data Index: 7393960 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5852. Min Act: -0.1700

Data Index: 4045649 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5866. Min Act: -0.1700

Data Index: 5332671 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5775. Min Act: -0.1700

Data Index: 6973869 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5695. Min Act: -0.1696

Data Index: 5499816 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5753. Min Act: -0.1642

Data Index: 1476274 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5638. Min Act: -0.1685

Data Index: 5495071 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5696. Min Act: -0.1676

Data Index: 4146171 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5655. Min Act: -0.1609

Data Index: 1614686 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5646. Min Act: -0.1690

Data Index: 6207719 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5617. Min Act: -0.1598

Data Index: 1073685 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5600. Min Act: -0.1695

Data Index: 3794670 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5536. Min Act: -0.1642

Data Index: 2605673 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 1.6501. Min Range: -1.6501

Max Act: 1.5548. Min Act: -0.1658

Data Index: 6964919 (Open Web Text)

Max Activating Token Index: 8