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

Dataset: Open Web Text

Neuron 2658 in Layer 4

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: 3.3826. Min Range: -3.3826

Max Act: 3.3826. Min Act: -0.1700

Data Index: 2567327 (Open Web Text)

Max Activating Token Index: 329

Text #1

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.3025. Min Act: -0.1700

Data Index: 57393 (Open Web Text)

Max Activating Token Index: 121

Text #2

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.2497. Min Act: -0.1700

Data Index: 2980206 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.2461. Min Act: -0.1700

Data Index: 8530129 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.1958. Min Act: -0.1700

Data Index: 7489102 (Open Web Text)

Max Activating Token Index: 583

Text #5

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.1614. Min Act: -0.1700

Data Index: 1821091 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.1513. Min Act: -0.1700

Data Index: 7295927 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.1441. Min Act: -0.1700

Data Index: 4797006 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.1014. Min Act: -0.1700

Data Index: 8456295 (Open Web Text)

Max Activating Token Index: 306

Text #9

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0870. Min Act: -0.1700

Data Index: 585330 (Open Web Text)

Max Activating Token Index: 165

Text #10

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.1202. Min Act: -0.1700

Data Index: 8456294 (Open Web Text)

Max Activating Token Index: 651

Text #11

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0919. Min Act: -0.1700

Data Index: 89484 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0684. Min Act: -0.1700

Data Index: 2184739 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.1005. Min Act: -0.1700

Data Index: 362347 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0692. Min Act: -0.1700

Data Index: 235552 (Open Web Text)

Max Activating Token Index: 75

Text #15

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0748. Min Act: -0.1700

Data Index: 362346 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0582. Min Act: -0.1700

Data Index: 250841 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0605. Min Act: -0.1700

Data Index: 6418404 (Open Web Text)

Max Activating Token Index: 897

Text #18

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0764. Min Act: -0.1700

Data Index: 5466426 (Open Web Text)

Max Activating Token Index: 741

Text #19

Max Range: 3.3826. Min Range: -3.3826

Max Act: 3.0555. Min Act: -0.1700

Data Index: 362349 (Open Web Text)

Max Activating Token Index: 17