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

Dataset: Open Web Text

Neuron 373 in Layer 1

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: 1.5670. Min Range: -1.5670

Max Act: 1.5665. Min Act: -0.1671

Data Index: 5138285 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5670. Min Act: -0.1700

Data Index: 2755521 (Open Web Text)

Max Activating Token Index: 729

Text #2

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5477. Min Act: -0.1700

Data Index: 6063901 (Open Web Text)

Max Activating Token Index: 339

Text #3

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5542. Min Act: -0.1699

Data Index: 1811636 (Open Web Text)

Max Activating Token Index: 331

Text #4

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5435. Min Act: -0.1700

Data Index: 926062 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5447. Min Act: -0.1632

Data Index: 5642007 (Open Web Text)

Max Activating Token Index: 757

Text #6

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5363. Min Act: -0.1680

Data Index: 2608727 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5391. Min Act: -0.1700

Data Index: 1017219 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5273. Min Act: -0.1700

Data Index: 419190 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5159. Min Act: -0.1643

Data Index: 3544929 (Open Web Text)

Max Activating Token Index: 324

Text #10

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5287. Min Act: -0.1700

Data Index: 282923 (Open Web Text)

Max Activating Token Index: 953

Text #11

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5194. Min Act: -0.1699

Data Index: 2931144 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5092. Min Act: -0.1700

Data Index: 2109609 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5090. Min Act: -0.1700

Data Index: 8363246 (Open Web Text)

Max Activating Token Index: 345

Text #14

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5094. Min Act: -0.1699

Data Index: 3020039 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5080. Min Act: -0.1693

Data Index: 7157277 (Open Web Text)

Max Activating Token Index: 913

Text #16

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5115. Min Act: -0.1680

Data Index: 8023295 (Open Web Text)

Max Activating Token Index: 824

Text #17

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5300. Min Act: -0.1700

Data Index: 6101009 (Open Web Text)

Max Activating Token Index: 816

Text #18

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.5056. Min Act: -0.1699

Data Index: 5128845 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 1.5670. Min Range: -1.5670

Max Act: 1.4993. Min Act: -0.1700

Data Index: 6162715 (Open Web Text)

Max Activating Token Index: 749