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

Dataset: Open Web Text

Neuron 1737 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: 4.8563. Min Range: -4.8563

Max Act: 4.8563. Min Act: -0.1700

Data Index: 1840526 (Open Web Text)

Max Activating Token Index: 920

Text #1

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.7398. Min Act: -0.1700

Data Index: 5119788 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.7454. Min Act: -0.1700

Data Index: 2576287 (Open Web Text)

Max Activating Token Index: 833

Text #3

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.7285. Min Act: -0.1700

Data Index: 1419323 (Open Web Text)

Max Activating Token Index: 822

Text #4

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6981. Min Act: -0.1700

Data Index: 7698289 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6526. Min Act: -0.1700

Data Index: 5902914 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.7141. Min Act: -0.1700

Data Index: 5065415 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6699. Min Act: -0.1700

Data Index: 4039273 (Open Web Text)

Max Activating Token Index: 884

Text #8

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6633. Min Act: -0.1700

Data Index: 2515371 (Open Web Text)

Max Activating Token Index: 625

Text #9

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6594. Min Act: -0.1700

Data Index: 3417347 (Open Web Text)

Max Activating Token Index: 619

Text #10

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6296. Min Act: -0.1700

Data Index: 7348353 (Open Web Text)

Max Activating Token Index: 651

Text #11

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6308. Min Act: -0.1700

Data Index: 282296 (Open Web Text)

Max Activating Token Index: 928

Text #12

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6282. Min Act: -0.1700

Data Index: 7874235 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6185. Min Act: -0.1700

Data Index: 2725236 (Open Web Text)

Max Activating Token Index: 766

Text #14

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6206. Min Act: -0.1700

Data Index: 2702961 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6172. Min Act: -0.1700

Data Index: 1655891 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.5861. Min Act: -0.1700

Data Index: 6461066 (Open Web Text)

Max Activating Token Index: 530

Text #17

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.5604. Min Act: -0.1700

Data Index: 6340029 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.5879. Min Act: -0.1700

Data Index: 4321856 (Open Web Text)

Max Activating Token Index: 585

Text #19

Max Range: 4.8563. Min Range: -4.8563

Max Act: 4.6001. Min Act: -0.1700

Data Index: 4070044 (Open Web Text)

Max Activating Token Index: 720