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

Dataset: Open Web Text

Neuron 2022 in Layer 5

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: 3.6498. Min Range: -3.6498

Max Act: 3.6498. Min Act: -0.1700

Data Index: 8129113 (Open Web Text)

Max Activating Token Index: 892

Text #1

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.4880. Min Act: -0.1700

Data Index: 2668162 (Open Web Text)

Max Activating Token Index: 675

Text #2

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.3699. Min Act: -0.1700

Data Index: 2948612 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.2694. Min Act: -0.1700

Data Index: 6366083 (Open Web Text)

Max Activating Token Index: 878

Text #4

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.2221. Min Act: -0.1700

Data Index: 1632516 (Open Web Text)

Max Activating Token Index: 377

Text #5

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.2113. Min Act: -0.1700

Data Index: 3271204 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.2039. Min Act: -0.1700

Data Index: 3419431 (Open Web Text)

Max Activating Token Index: 534

Text #7

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.2157. Min Act: -0.1700

Data Index: 5261851 (Open Web Text)

Max Activating Token Index: 779

Text #8

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.1500. Min Act: -0.1700

Data Index: 1820093 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.1820. Min Act: -0.1700

Data Index: 4228665 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.1396. Min Act: -0.1700

Data Index: 1022220 (Open Web Text)

Max Activating Token Index: 985

Text #11

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.1372. Min Act: -0.1700

Data Index: 6304298 (Open Web Text)

Max Activating Token Index: 781

Text #12

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.1391. Min Act: -0.1700

Data Index: 8410365 (Open Web Text)

Max Activating Token Index: 843

Text #13

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.1394. Min Act: -0.1700

Data Index: 4664721 (Open Web Text)

Max Activating Token Index: 417

Text #14

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.0690. Min Act: -0.1700

Data Index: 4206163 (Open Web Text)

Max Activating Token Index: 857

Text #15

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.1043. Min Act: -0.1700

Data Index: 6157544 (Open Web Text)

Max Activating Token Index: 446

Text #16

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.0885. Min Act: -0.1700

Data Index: 7643766 (Open Web Text)

Max Activating Token Index: 755

Text #17

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.0698. Min Act: -0.1700

Data Index: 3817076 (Open Web Text)

Max Activating Token Index: 570

Text #18

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.0634. Min Act: -0.1700

Data Index: 6890535 (Open Web Text)

Max Activating Token Index: 675

Text #19

Max Range: 3.6498. Min Range: -3.6498

Max Act: 3.0410. Min Act: -0.1700

Data Index: 1333537 (Open Web Text)

Max Activating Token Index: 976