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

Dataset: Open Web Text

Neuron 1856 in Layer 3

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: 3.8677. Min Range: -3.8677

Max Act: 3.8677. Min Act: -0.1700

Data Index: 913099 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.8583. Min Act: -0.1700

Data Index: 8734911 (Open Web Text)

Max Activating Token Index: 870

Text #2

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7861. Min Act: -0.1700

Data Index: 8471717 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7849. Min Act: -0.1700

Data Index: 1676680 (Open Web Text)

Max Activating Token Index: 67

Text #4

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7775. Min Act: -0.1700

Data Index: 6517223 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7246. Min Act: -0.1700

Data Index: 2062281 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7645. Min Act: -0.1700

Data Index: 4352569 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7344. Min Act: -0.1700

Data Index: 8659526 (Open Web Text)

Max Activating Token Index: 670

Text #8

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7518. Min Act: -0.1700

Data Index: 6829901 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7523. Min Act: -0.1700

Data Index: 462440 (Open Web Text)

Max Activating Token Index: 892

Text #10

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7010. Min Act: -0.1700

Data Index: 4133733 (Open Web Text)

Max Activating Token Index: 154

Text #11

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7233. Min Act: -0.1700

Data Index: 295689 (Open Web Text)

Max Activating Token Index: 391

Text #12

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7306. Min Act: -0.1700

Data Index: 3992245 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7247. Min Act: -0.1700

Data Index: 7210234 (Open Web Text)

Max Activating Token Index: 539

Text #14

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7315. Min Act: -0.1700

Data Index: 2551755 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7207. Min Act: -0.1700

Data Index: 2429555 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.6778. Min Act: -0.1700

Data Index: 5930732 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7023. Min Act: -0.1700

Data Index: 5383956 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7540. Min Act: -0.1700

Data Index: 1875766 (Open Web Text)

Max Activating Token Index: 622

Text #19

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.6866. Min Act: -0.1700

Data Index: 1837367 (Open Web Text)

Max Activating Token Index: 703