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

Dataset: Open Web Text

Neuron 1784 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: 1.2634. Min Range: -1.2634

Max Act: 1.2634. Min Act: -0.1700

Data Index: 5402444 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.2222. Min Act: -0.1700

Data Index: 7455240 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.2085. Min Act: -0.1682

Data Index: 5758166 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1902. Min Act: -0.1672

Data Index: 585839 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1788. Min Act: -0.1599

Data Index: 3883763 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1846. Min Act: -0.1694

Data Index: 7913104 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1830. Min Act: -0.1678

Data Index: 6098113 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1758. Min Act: -0.1589

Data Index: 2066589 (Open Web Text)

Max Activating Token Index: 563

Text #8

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1812. Min Act: -0.1700

Data Index: 3736499 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1727. Min Act: -0.1644

Data Index: 3762006 (Open Web Text)

Max Activating Token Index: 679

Text #10

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1734. Min Act: -0.1679

Data Index: 874595 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1655. Min Act: -0.1674

Data Index: 7638459 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1683. Min Act: -0.1700

Data Index: 5584356 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1611. Min Act: -0.1655

Data Index: 6423833 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1565. Min Act: -0.1700

Data Index: 6085659 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1537. Min Act: -0.1612

Data Index: 5832072 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1514. Min Act: -0.1700

Data Index: 7867274 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1600. Min Act: -0.1700

Data Index: 2071980 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1593. Min Act: -0.1571

Data Index: 1219472 (Open Web Text)

Max Activating Token Index: 357

Text #19

Max Range: 1.2634. Min Range: -1.2634

Max Act: 1.1610. Min Act: -0.1668

Data Index: 5786600 (Open Web Text)

Max Activating Token Index: 278