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

Dataset: Open Web Text

Neuron 71 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: 1.9677. Min Range: -1.9677

Max Act: 1.9677. Min Act: -0.1700

Data Index: 3940397 (Open Web Text)

Max Activating Token Index: 939

Text #1

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8843. Min Act: -0.1699

Data Index: 4099372 (Open Web Text)

Max Activating Token Index: 700

Text #2

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8738. Min Act: -0.1700

Data Index: 73294 (Open Web Text)

Max Activating Token Index: 911

Text #3

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8778. Min Act: -0.1700

Data Index: 1459526 (Open Web Text)

Max Activating Token Index: 778

Text #4

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8529. Min Act: -0.1700

Data Index: 6485092 (Open Web Text)

Max Activating Token Index: 916

Text #5

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8733. Min Act: -0.1700

Data Index: 2442408 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8463. Min Act: -0.1700

Data Index: 5377486 (Open Web Text)

Max Activating Token Index: 1018

Text #7

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8526. Min Act: -0.1700

Data Index: 5938247 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8506. Min Act: -0.1699

Data Index: 464686 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8447. Min Act: -0.1700

Data Index: 8369001 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8507. Min Act: -0.1700

Data Index: 6786569 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8423. Min Act: -0.1700

Data Index: 8525035 (Open Web Text)

Max Activating Token Index: 493

Text #12

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8313. Min Act: -0.1700

Data Index: 7179130 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8261. Min Act: -0.1700

Data Index: 7395147 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8239. Min Act: -0.1700

Data Index: 464181 (Open Web Text)

Max Activating Token Index: 734

Text #15

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8172. Min Act: -0.1700

Data Index: 8143037 (Open Web Text)

Max Activating Token Index: 873

Text #16

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8144. Min Act: -0.1700

Data Index: 3223155 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8308. Min Act: -0.1700

Data Index: 15565 (Open Web Text)

Max Activating Token Index: 739

Text #18

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8138. Min Act: -0.1700

Data Index: 6533392 (Open Web Text)

Max Activating Token Index: 528

Text #19

Max Range: 1.9677. Min Range: -1.9677

Max Act: 1.8217. Min Act: -0.1700

Data Index: 7330130 (Open Web Text)

Max Activating Token Index: 69