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

Dataset: Open Web Text

Neuron 1246 in Layer 6

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: 4.4616. Min Range: -4.4616

Max Act: 4.4616. Min Act: -0.1700

Data Index: 7456107 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.4587. Min Act: -0.1700

Data Index: 1885966 (Open Web Text)

Max Activating Token Index: 720

Text #2

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.2866. Min Act: -0.1700

Data Index: 8301944 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1619. Min Act: -0.1700

Data Index: 2790597 (Open Web Text)

Max Activating Token Index: 331

Text #4

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1856. Min Act: -0.1700

Data Index: 6393124 (Open Web Text)

Max Activating Token Index: 990

Text #5

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1328. Min Act: -0.1700

Data Index: 2249883 (Open Web Text)

Max Activating Token Index: 704

Text #6

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1750. Min Act: -0.1700

Data Index: 7999005 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1157. Min Act: -0.1700

Data Index: 8803098 (Open Web Text)

Max Activating Token Index: 945

Text #8

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1484. Min Act: -0.1700

Data Index: 6937672 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1547. Min Act: -0.1700

Data Index: 1341775 (Open Web Text)

Max Activating Token Index: 799

Text #10

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0806. Min Act: -0.1700

Data Index: 3296228 (Open Web Text)

Max Activating Token Index: 934

Text #11

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1065. Min Act: -0.1700

Data Index: 1452322 (Open Web Text)

Max Activating Token Index: 864

Text #12

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0827. Min Act: -0.1700

Data Index: 1897125 (Open Web Text)

Max Activating Token Index: 418

Text #13

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.1589. Min Act: -0.1700

Data Index: 6827417 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0812. Min Act: -0.1700

Data Index: 1769982 (Open Web Text)

Max Activating Token Index: 783

Text #15

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0539. Min Act: -0.1700

Data Index: 5183867 (Open Web Text)

Max Activating Token Index: 475

Text #16

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0917. Min Act: -0.1700

Data Index: 1167805 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0839. Min Act: -0.1700

Data Index: 7085139 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0762. Min Act: -0.1700

Data Index: 4490763 (Open Web Text)

Max Activating Token Index: 855

Text #19

Max Range: 4.4616. Min Range: -4.4616

Max Act: 4.0588. Min Act: -0.1700

Data Index: 2700332 (Open Web Text)

Max Activating Token Index: 461