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

Dataset: Open Web Text

Neuron 3035 in Layer 6

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: 5.0357. Min Range: -5.0357

Max Act: 5.0357. Min Act: -0.1700

Data Index: 945421 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9972. Min Act: -0.1700

Data Index: 1134896 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9530. Min Act: -0.1700

Data Index: 5179133 (Open Web Text)

Max Activating Token Index: 210

Text #3

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9492. Min Act: -0.1700

Data Index: 1038887 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9578. Min Act: -0.1700

Data Index: 6686138 (Open Web Text)

Max Activating Token Index: 586

Text #5

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9399. Min Act: -0.1700

Data Index: 6677920 (Open Web Text)

Max Activating Token Index: 970

Text #6

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9619. Min Act: -0.1700

Data Index: 4932372 (Open Web Text)

Max Activating Token Index: 634

Text #7

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9442. Min Act: -0.1700

Data Index: 2896187 (Open Web Text)

Max Activating Token Index: 882

Text #8

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9099. Min Act: -0.1700

Data Index: 7629922 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9197. Min Act: -0.1700

Data Index: 3635976 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9125. Min Act: -0.1700

Data Index: 310338 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9283. Min Act: -0.1700

Data Index: 3903418 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9077. Min Act: -0.1700

Data Index: 2638467 (Open Web Text)

Max Activating Token Index: 145

Text #13

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.8591. Min Act: -0.1700

Data Index: 6765937 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.8915. Min Act: -0.1700

Data Index: 6677919 (Open Web Text)

Max Activating Token Index: 954

Text #15

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.8837. Min Act: -0.1700

Data Index: 7098062 (Open Web Text)

Max Activating Token Index: 282

Text #16

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.8783. Min Act: -0.1700

Data Index: 4663039 (Open Web Text)

Max Activating Token Index: 151

Text #17

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9025. Min Act: -0.1700

Data Index: 4024260 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.9082. Min Act: -0.1700

Data Index: 5283258 (Open Web Text)

Max Activating Token Index: 272

Text #19

Max Range: 5.0357. Min Range: -5.0357

Max Act: 4.8501. Min Act: -0.1700

Data Index: 3391340 (Open Web Text)

Max Activating Token Index: 945