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

Dataset: Open Web Text

Neuron 1456 in Layer 0

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: 3.0268. Min Range: -3.0268

Max Act: 3.0268. Min Act: -0.1700

Data Index: 5165426 (Open Web Text)

Max Activating Token Index: 828

Text #1

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8774. Min Act: -0.1700

Data Index: 4584606 (Open Web Text)

Max Activating Token Index: 991

Text #2

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8860. Min Act: -0.1700

Data Index: 6162867 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8968. Min Act: -0.1700

Data Index: 6162866 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8465. Min Act: -0.1700

Data Index: 6179805 (Open Web Text)

Max Activating Token Index: 174

Text #5

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8245. Min Act: -0.1700

Data Index: 80594 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8166. Min Act: -0.1700

Data Index: 6162865 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8069. Min Act: -0.1700

Data Index: 4542291 (Open Web Text)

Max Activating Token Index: 834

Text #8

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8012. Min Act: -0.1700

Data Index: 5340280 (Open Web Text)

Max Activating Token Index: 504

Text #9

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.8051. Min Act: -0.1700

Data Index: 2604672 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7977. Min Act: -0.1700

Data Index: 5925861 (Open Web Text)

Max Activating Token Index: 333

Text #11

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7676. Min Act: -0.1700

Data Index: 8277468 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7732. Min Act: -0.1700

Data Index: 8624141 (Open Web Text)

Max Activating Token Index: 803

Text #13

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7602. Min Act: -0.1700

Data Index: 5679004 (Open Web Text)

Max Activating Token Index: 109

Text #14

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7583. Min Act: -0.1700

Data Index: 62463 (Open Web Text)

Max Activating Token Index: 311

Text #15

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7431. Min Act: -0.1700

Data Index: 7969202 (Open Web Text)

Max Activating Token Index: 88

Text #16

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7418. Min Act: -0.1700

Data Index: 7369206 (Open Web Text)

Max Activating Token Index: 440

Text #17

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7279. Min Act: -0.1700

Data Index: 1717500 (Open Web Text)

Max Activating Token Index: 688

Text #18

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7345. Min Act: -0.1700

Data Index: 4383865 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 3.0268. Min Range: -3.0268

Max Act: 2.7336. Min Act: -0.1700

Data Index: 3847915 (Open Web Text)

Max Activating Token Index: 327