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

Dataset: Open Web Text

Neuron 1216 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: 1.9587. Min Range: -1.9587

Max Act: 1.9587. Min Act: -0.1700

Data Index: 3046314 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.9391. Min Act: -0.1700

Data Index: 2782457 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.9183. Min Act: -0.1700

Data Index: 6118102 (Open Web Text)

Max Activating Token Index: 778

Text #3

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8722. Min Act: -0.1700

Data Index: 7057835 (Open Web Text)

Max Activating Token Index: 603

Text #4

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8561. Min Act: -0.1700

Data Index: 1007371 (Open Web Text)

Max Activating Token Index: 702

Text #5

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8379. Min Act: -0.1700

Data Index: 6872072 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8427. Min Act: -0.1700

Data Index: 8174204 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8495. Min Act: -0.1700

Data Index: 1335623 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8402. Min Act: -0.1700

Data Index: 3482338 (Open Web Text)

Max Activating Token Index: 47

Text #9

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8176. Min Act: -0.1700

Data Index: 561743 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8141. Min Act: -0.1700

Data Index: 8261893 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.8089. Min Act: -0.1700

Data Index: 7579108 (Open Web Text)

Max Activating Token Index: 689

Text #12

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7903. Min Act: -0.1700

Data Index: 2169246 (Open Web Text)

Max Activating Token Index: 1007

Text #13

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7801. Min Act: -0.1700

Data Index: 1647250 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7922. Min Act: -0.1700

Data Index: 862151 (Open Web Text)

Max Activating Token Index: 613

Text #15

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7817. Min Act: -0.1700

Data Index: 4825976 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7771. Min Act: -0.1700

Data Index: 5590454 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7928. Min Act: -0.1700

Data Index: 6231182 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7758. Min Act: -0.1700

Data Index: 888085 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 1.9587. Min Range: -1.9587

Max Act: 1.7602. Min Act: -0.1700

Data Index: 4591159 (Open Web Text)

Max Activating Token Index: 570