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

Dataset: Open Web Text

Neuron 1321 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: 4.1608. Min Range: -4.1608

Max Act: 4.1608. Min Act: -0.1700

Data Index: 841966 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 4.1608. Min Range: -4.1608

Max Act: 4.1044. Min Act: -0.1700

Data Index: 8671487 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 4.1608. Min Range: -4.1608

Max Act: 4.0700. Min Act: -0.1700

Data Index: 8716079 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 4.1608. Min Range: -4.1608

Max Act: 4.0497. Min Act: -0.1700

Data Index: 4379667 (Open Web Text)

Max Activating Token Index: 807

Text #4

Max Range: 4.1608. Min Range: -4.1608

Max Act: 4.0334. Min Act: -0.1700

Data Index: 4892318 (Open Web Text)

Max Activating Token Index: 115

Text #5

Max Range: 4.1608. Min Range: -4.1608

Max Act: 4.0340. Min Act: -0.1700

Data Index: 8128417 (Open Web Text)

Max Activating Token Index: 550

Text #6

Max Range: 4.1608. Min Range: -4.1608

Max Act: 4.0028. Min Act: -0.1700

Data Index: 4007398 (Open Web Text)

Max Activating Token Index: 744

Text #7

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9858. Min Act: -0.1700

Data Index: 2756121 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 4.1608. Min Range: -4.1608

Max Act: 4.0070. Min Act: -0.1700

Data Index: 5937215 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9757. Min Act: -0.1700

Data Index: 2394621 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9526. Min Act: -0.1700

Data Index: 6815850 (Open Web Text)

Max Activating Token Index: 172

Text #11

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9650. Min Act: -0.1700

Data Index: 6211243 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9763. Min Act: -0.1700

Data Index: 12795 (Open Web Text)

Max Activating Token Index: 936

Text #13

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9423. Min Act: -0.1700

Data Index: 2362629 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9570. Min Act: -0.1700

Data Index: 6517980 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9719. Min Act: -0.1700

Data Index: 5168951 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9405. Min Act: -0.1700

Data Index: 6622382 (Open Web Text)

Max Activating Token Index: 929

Text #17

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9200. Min Act: -0.1700

Data Index: 1150463 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9264. Min Act: -0.1700

Data Index: 3783582 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 4.1608. Min Range: -4.1608

Max Act: 3.9479. Min Act: -0.1700

Data Index: 1559733 (Open Web Text)

Max Activating Token Index: 835