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

Dataset: Open Web Text

Neuron 463 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: 5.0583. Min Range: -5.0583

Max Act: 5.0583. Min Act: -0.1700

Data Index: 3275828 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 5.0583. Min Range: -5.0583

Max Act: 5.0555. Min Act: -0.1700

Data Index: 4174487 (Open Web Text)

Max Activating Token Index: 639

Text #2

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.9809. Min Act: -0.1700

Data Index: 3791028 (Open Web Text)

Max Activating Token Index: 587

Text #3

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.9559. Min Act: -0.1700

Data Index: 8354266 (Open Web Text)

Max Activating Token Index: 383

Text #4

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.9360. Min Act: -0.1700

Data Index: 3085451 (Open Web Text)

Max Activating Token Index: 350

Text #5

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.9540. Min Act: -0.1700

Data Index: 1086320 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.9356. Min Act: -0.1700

Data Index: 748215 (Open Web Text)

Max Activating Token Index: 421

Text #7

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.9051. Min Act: -0.1700

Data Index: 503868 (Open Web Text)

Max Activating Token Index: 869

Text #8

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.9351. Min Act: -0.1700

Data Index: 4189019 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8627. Min Act: -0.1700

Data Index: 6507021 (Open Web Text)

Max Activating Token Index: 667

Text #10

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8686. Min Act: -0.1700

Data Index: 7931265 (Open Web Text)

Max Activating Token Index: 166

Text #11

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8787. Min Act: -0.1700

Data Index: 3666795 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8840. Min Act: -0.1700

Data Index: 7016166 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8453. Min Act: -0.1700

Data Index: 1201609 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8256. Min Act: -0.1700

Data Index: 7989311 (Open Web Text)

Max Activating Token Index: 198

Text #15

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8413. Min Act: -0.1700

Data Index: 4224401 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8082. Min Act: -0.1700

Data Index: 2539818 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8245. Min Act: -0.1700

Data Index: 2009341 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8298. Min Act: -0.1700

Data Index: 2461131 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 5.0583. Min Range: -5.0583

Max Act: 4.8677. Min Act: -0.1700

Data Index: 3261599 (Open Web Text)

Max Activating Token Index: 547