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

Dataset: Open Web Text

Neuron 2344 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: 1.1974. Min Range: -1.1974

Max Act: 1.1974. Min Act: -0.1173

Data Index: 2115554 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1956. Min Act: -0.0893

Data Index: 2343196 (Open Web Text)

Max Activating Token Index: 836

Text #2

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1807. Min Act: -0.0452

Data Index: 3269012 (Open Web Text)

Max Activating Token Index: 793

Text #3

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1788. Min Act: -0.1627

Data Index: 892447 (Open Web Text)

Max Activating Token Index: 804

Text #4

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1798. Min Act: -0.1351

Data Index: 6760721 (Open Web Text)

Max Activating Token Index: 784

Text #5

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1779. Min Act: -0.1073

Data Index: 5697008 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1763. Min Act: -0.0924

Data Index: 2115559 (Open Web Text)

Max Activating Token Index: 805

Text #7

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1791. Min Act: -0.0353

Data Index: 7859412 (Open Web Text)

Max Activating Token Index: 804

Text #8

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1729. Min Act: -0.1371

Data Index: 6999180 (Open Web Text)

Max Activating Token Index: 813

Text #9

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1733. Min Act: -0.1304

Data Index: 4303147 (Open Web Text)

Max Activating Token Index: 810

Text #10

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1735. Min Act: -0.0833

Data Index: 3138780 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1721. Min Act: -0.1198

Data Index: 1204688 (Open Web Text)

Max Activating Token Index: 746

Text #12

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1715. Min Act: -0.1323

Data Index: 4175809 (Open Web Text)

Max Activating Token Index: 809

Text #13

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1660. Min Act: -0.0987

Data Index: 5796319 (Open Web Text)

Max Activating Token Index: 794

Text #14

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1675. Min Act: -0.1526

Data Index: 7859411 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1692. Min Act: -0.0090

Data Index: 3269011 (Open Web Text)

Max Activating Token Index: 783

Text #16

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1687. Min Act: -0.0452

Data Index: 1718647 (Open Web Text)

Max Activating Token Index: 797

Text #17

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1646. Min Act: -0.0598

Data Index: 3414699 (Open Web Text)

Max Activating Token Index: 799

Text #18

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1629. Min Act: -0.1323

Data Index: 3763425 (Open Web Text)

Max Activating Token Index: 824

Text #19

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1633. Min Act: -0.1200

Data Index: 4167191 (Open Web Text)

Max Activating Token Index: 801