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

Dataset: Open Web Text

Neuron 815 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: 4.5612. Min Range: -4.5612

Max Act: 4.5612. Min Act: -0.1700

Data Index: 5481120 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.5292. Min Act: -0.1700

Data Index: 322730 (Open Web Text)

Max Activating Token Index: 196

Text #2

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.5530. Min Act: -0.1700

Data Index: 1675259 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.5354. Min Act: -0.1700

Data Index: 2174632 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.5052. Min Act: -0.1700

Data Index: 433730 (Open Web Text)

Max Activating Token Index: 429

Text #5

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.5141. Min Act: -0.1700

Data Index: 2914171 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4709. Min Act: -0.1700

Data Index: 5876509 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4648. Min Act: -0.1700

Data Index: 1787932 (Open Web Text)

Max Activating Token Index: 263

Text #8

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.5020. Min Act: -0.1700

Data Index: 2335905 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4602. Min Act: -0.1700

Data Index: 1697564 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4842. Min Act: -0.1700

Data Index: 2066463 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4919. Min Act: -0.1700

Data Index: 4230541 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4736. Min Act: -0.1700

Data Index: 5372057 (Open Web Text)

Max Activating Token Index: 697

Text #13

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4354. Min Act: -0.1700

Data Index: 1548441 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4606. Min Act: -0.1700

Data Index: 2365879 (Open Web Text)

Max Activating Token Index: 477

Text #15

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4306. Min Act: -0.1700

Data Index: 2430104 (Open Web Text)

Max Activating Token Index: 460

Text #16

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4346. Min Act: -0.1700

Data Index: 1251342 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4391. Min Act: -0.1700

Data Index: 2457918 (Open Web Text)

Max Activating Token Index: 827

Text #18

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4399. Min Act: -0.1700

Data Index: 4951122 (Open Web Text)

Max Activating Token Index: 512

Text #19

Max Range: 4.5612. Min Range: -4.5612

Max Act: 4.4373. Min Act: -0.1700

Data Index: 5137012 (Open Web Text)

Max Activating Token Index: 955