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

Dataset: Open Web Text

Neuron 644 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: 5.3203. Min Range: -5.3203

Max Act: 5.3203. Min Act: -0.1700

Data Index: 382530 (Open Web Text)

Max Activating Token Index: 1001

Text #1

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.2489. Min Act: -0.1700

Data Index: 212301 (Open Web Text)

Max Activating Token Index: 383

Text #2

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.1753. Min Act: -0.1700

Data Index: 6344832 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.1656. Min Act: -0.1700

Data Index: 729202 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.2072. Min Act: -0.1700

Data Index: 6344833 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.1525. Min Act: -0.1700

Data Index: 5169519 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.1526. Min Act: -0.1700

Data Index: 8363646 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.1846. Min Act: -0.1700

Data Index: 5036404 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.1356. Min Act: -0.1700

Data Index: 8191085 (Open Web Text)

Max Activating Token Index: 926

Text #9

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0734. Min Act: -0.1700

Data Index: 8227248 (Open Web Text)

Max Activating Token Index: 432

Text #10

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0806. Min Act: -0.1700

Data Index: 1371554 (Open Web Text)

Max Activating Token Index: 729

Text #11

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0847. Min Act: -0.1700

Data Index: 1674843 (Open Web Text)

Max Activating Token Index: 449

Text #12

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0953. Min Act: -0.1700

Data Index: 3576406 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0732. Min Act: -0.1700

Data Index: 1861509 (Open Web Text)

Max Activating Token Index: 233

Text #14

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0896. Min Act: -0.1700

Data Index: 8147316 (Open Web Text)

Max Activating Token Index: 120

Text #15

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0332. Min Act: -0.1700

Data Index: 6436220 (Open Web Text)

Max Activating Token Index: 451

Text #16

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0742. Min Act: -0.1700

Data Index: 2699062 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0058. Min Act: -0.1700

Data Index: 455775 (Open Web Text)

Max Activating Token Index: 331

Text #18

Max Range: 5.3203. Min Range: -5.3203

Max Act: 5.0485. Min Act: -0.1700

Data Index: 2586273 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 5.3203. Min Range: -5.3203

Max Act: 4.9966. Min Act: -0.1700

Data Index: 4591487 (Open Web Text)

Max Activating Token Index: 941