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

Dataset: Open Web Text

Neuron 1251 in Layer 3

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: 3.4841. Min Range: -3.4841

Max Act: 3.4841. Min Act: -0.1700

Data Index: 4192798 (Open Web Text)

Max Activating Token Index: 869

Text #1

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.4352. Min Act: -0.1700

Data Index: 340507 (Open Web Text)

Max Activating Token Index: 626

Text #2

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.2709. Min Act: -0.1700

Data Index: 8712940 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.2876. Min Act: -0.1700

Data Index: 8047981 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.2465. Min Act: -0.1700

Data Index: 8389944 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.2339. Min Act: -0.1700

Data Index: 2855883 (Open Web Text)

Max Activating Token Index: 411

Text #6

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.2178. Min Act: -0.1700

Data Index: 5685201 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1803. Min Act: -0.1700

Data Index: 3743625 (Open Web Text)

Max Activating Token Index: 801

Text #8

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1807. Min Act: -0.1700

Data Index: 5788789 (Open Web Text)

Max Activating Token Index: 539

Text #9

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1725. Min Act: -0.1700

Data Index: 2997672 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1189. Min Act: -0.1700

Data Index: 1345272 (Open Web Text)

Max Activating Token Index: 287

Text #11

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1351. Min Act: -0.1700

Data Index: 2151634 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.0947. Min Act: -0.1700

Data Index: 255817 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1253. Min Act: -0.1700

Data Index: 3952039 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1027. Min Act: -0.1700

Data Index: 3648469 (Open Web Text)

Max Activating Token Index: 777

Text #15

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.0975. Min Act: -0.1700

Data Index: 6252250 (Open Web Text)

Max Activating Token Index: 602

Text #16

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.0908. Min Act: -0.1700

Data Index: 345889 (Open Web Text)

Max Activating Token Index: 67

Text #17

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.0841. Min Act: -0.1700

Data Index: 2005174 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.0818. Min Act: -0.1700

Data Index: 4316926 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 3.4841. Min Range: -3.4841

Max Act: 3.1001. Min Act: -0.1700

Data Index: 3444348 (Open Web Text)

Max Activating Token Index: 264