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

Dataset: Open Web Text

Neuron 2667 in Layer 4

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: 5.6785. Min Range: -5.6785

Max Act: 5.6785. Min Act: -0.1700

Data Index: 2397607 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.6220. Min Act: -0.1700

Data Index: 5692169 (Open Web Text)

Max Activating Token Index: 64

Text #2

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.5933. Min Act: -0.1700

Data Index: 8134378 (Open Web Text)

Max Activating Token Index: 882

Text #3

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.6260. Min Act: -0.1700

Data Index: 8661386 (Open Web Text)

Max Activating Token Index: 358

Text #4

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.5778. Min Act: -0.1700

Data Index: 6570455 (Open Web Text)

Max Activating Token Index: 664

Text #5

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.5637. Min Act: -0.1700

Data Index: 4332486 (Open Web Text)

Max Activating Token Index: 331

Text #6

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.5492. Min Act: -0.1700

Data Index: 7299352 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.5209. Min Act: -0.1700

Data Index: 4421235 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4639. Min Act: -0.1700

Data Index: 2411400 (Open Web Text)

Max Activating Token Index: 96

Text #9

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4470. Min Act: -0.1700

Data Index: 3514186 (Open Web Text)

Max Activating Token Index: 521

Text #10

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4624. Min Act: -0.1700

Data Index: 951106 (Open Web Text)

Max Activating Token Index: 481

Text #11

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4981. Min Act: -0.1700

Data Index: 2983896 (Open Web Text)

Max Activating Token Index: 1016

Text #12

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4259. Min Act: -0.1700

Data Index: 5517242 (Open Web Text)

Max Activating Token Index: 725

Text #13

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4733. Min Act: -0.1700

Data Index: 4524090 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4412. Min Act: -0.1698

Data Index: 6714494 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4168. Min Act: -0.1700

Data Index: 118520 (Open Web Text)

Max Activating Token Index: 145

Text #16

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4038. Min Act: -0.1700

Data Index: 4465028 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.3771. Min Act: -0.1700

Data Index: 2507687 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.4097. Min Act: -0.1700

Data Index: 7379681 (Open Web Text)

Max Activating Token Index: 898

Text #19

Max Range: 5.6785. Min Range: -5.6785

Max Act: 5.3933. Min Act: -0.1700

Data Index: 290382 (Open Web Text)

Max Activating Token Index: 148