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

Dataset: Open Web Text

Neuron 1907 in Layer 2

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: 1.9419. Min Range: -1.9419

Max Act: 1.9419. Min Act: -0.1462

Data Index: 4834775 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.7299. Min Act: -0.1695

Data Index: 3098677 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.7206. Min Act: -0.1700

Data Index: 1045739 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.7058. Min Act: -0.1683

Data Index: 4983416 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.7229. Min Act: -0.1700

Data Index: 1287999 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.7119. Min Act: -0.1486

Data Index: 5456229 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6969. Min Act: -0.1687

Data Index: 7223974 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6776. Min Act: -0.1700

Data Index: 5174315 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6696. Min Act: -0.1690

Data Index: 102519 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6596. Min Act: -0.0805

Data Index: 6734156 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6485. Min Act: -0.1700

Data Index: 732513 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6475. Min Act: -0.1664

Data Index: 6295672 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6468. Min Act: -0.1700

Data Index: 5392797 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6435. Min Act: -0.1576

Data Index: 6023451 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6383. Min Act: -0.1700

Data Index: 5924122 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6343. Min Act: -0.1688

Data Index: 2531904 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6124. Min Act: -0.1501

Data Index: 1699342 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6203. Min Act: -0.1673

Data Index: 7632412 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6030. Min Act: -0.1700

Data Index: 1990960 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 1.9419. Min Range: -1.9419

Max Act: 1.6133. Min Act: -0.1698

Data Index: 5646929 (Open Web Text)

Max Activating Token Index: 1023