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

Dataset: Open Web Text

Neuron 1781 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: 1.1060. Min Range: -1.1060

Max Act: 1.1060. Min Act: -0.1549

Data Index: 3792297 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0958. Min Act: -0.1621

Data Index: 5282128 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0623. Min Act: -0.1686

Data Index: 3737269 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0114. Min Act: -0.1536

Data Index: 8012436 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0114. Min Act: -0.1481

Data Index: 5626494 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0158. Min Act: -0.1695

Data Index: 2647613 (Open Web Text)

Max Activating Token Index: 579

Text #6

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0114. Min Act: -0.1458

Data Index: 4119205 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0140. Min Act: -0.1636

Data Index: 5337678 (Open Web Text)

Max Activating Token Index: 72

Text #8

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0114. Min Act: -0.1472

Data Index: 7575463 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0114. Min Act: -0.1625

Data Index: 1984070 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0114. Min Act: -0.1633

Data Index: 8758840 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0029. Min Act: -0.1550

Data Index: 3711207 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9913. Min Act: -0.1629

Data Index: 3707326 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9777. Min Act: -0.1539

Data Index: 1382912 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9766. Min Act: -0.1658

Data Index: 3707324 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9793. Min Act: -0.1700

Data Index: 3493676 (Open Web Text)

Max Activating Token Index: 225

Text #16

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9826. Min Act: -0.1613

Data Index: 5302679 (Open Web Text)

Max Activating Token Index: 91

Text #17

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9853. Min Act: -0.1676

Data Index: 31861 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9837. Min Act: -0.1633

Data Index: 3430067 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9832. Min Act: -0.1526

Data Index: 1903903 (Open Web Text)

Max Activating Token Index: 156