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

Dataset: Open Web Text

Neuron 1645 in Layer 5

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: 6.5881. Min Range: -6.5881

Max Act: 6.5881. Min Act: -0.1700

Data Index: 7373210 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.4976. Min Act: -0.1700

Data Index: 6664584 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.4849. Min Act: -0.1700

Data Index: 5618361 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.3523. Min Act: -0.1700

Data Index: 2813566 (Open Web Text)

Max Activating Token Index: 921

Text #4

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.4083. Min Act: -0.1700

Data Index: 8640181 (Open Web Text)

Max Activating Token Index: 864

Text #5

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.4193. Min Act: -0.1700

Data Index: 6132399 (Open Web Text)

Max Activating Token Index: 439

Text #6

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.3562. Min Act: -0.1700

Data Index: 6842428 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2830. Min Act: -0.1700

Data Index: 3193104 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2800. Min Act: -0.1700

Data Index: 1051993 (Open Web Text)

Max Activating Token Index: 879

Text #9

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2124. Min Act: -0.1700

Data Index: 7980223 (Open Web Text)

Max Activating Token Index: 167

Text #10

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2260. Min Act: -0.1700

Data Index: 4358075 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2253. Min Act: -0.1700

Data Index: 7916782 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2264. Min Act: -0.1700

Data Index: 6333639 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2793. Min Act: -0.1700

Data Index: 1456341 (Open Web Text)

Max Activating Token Index: 785

Text #14

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2036. Min Act: -0.1700

Data Index: 2418101 (Open Web Text)

Max Activating Token Index: 655

Text #15

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2896. Min Act: -0.1700

Data Index: 6479639 (Open Web Text)

Max Activating Token Index: 843

Text #16

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2107. Min Act: -0.1700

Data Index: 235253 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.1559. Min Act: -0.1700

Data Index: 5982682 (Open Web Text)

Max Activating Token Index: 358

Text #18

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.2188. Min Act: -0.1700

Data Index: 5180959 (Open Web Text)

Max Activating Token Index: 411

Text #19

Max Range: 6.5881. Min Range: -6.5881

Max Act: 6.1443. Min Act: -0.1700

Data Index: 598312 (Open Web Text)

Max Activating Token Index: 4