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

Dataset: Open Web Text

Neuron 1366 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: 4.2686. Min Range: -4.2686

Max Act: 4.2686. Min Act: -0.1700

Data Index: 6068423 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.9908. Min Act: -0.1696

Data Index: 6068420 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.9460. Min Act: -0.1699

Data Index: 6068440 (Open Web Text)

Max Activating Token Index: 39

Text #3

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.9039. Min Act: -0.1700

Data Index: 4479097 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8938. Min Act: -0.1693

Data Index: 6068435 (Open Web Text)

Max Activating Token Index: 112

Text #5

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8644. Min Act: -0.1700

Data Index: 6068422 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8709. Min Act: -0.1677

Data Index: 1477585 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8606. Min Act: -0.1681

Data Index: 6068425 (Open Web Text)

Max Activating Token Index: 41

Text #8

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8680. Min Act: -0.1700

Data Index: 6068437 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8528. Min Act: -0.1699

Data Index: 6068418 (Open Web Text)

Max Activating Token Index: 796

Text #10

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8260. Min Act: -0.1700

Data Index: 6068421 (Open Web Text)

Max Activating Token Index: 149

Text #11

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8239. Min Act: -0.1700

Data Index: 6140845 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.8070. Min Act: -0.1700

Data Index: 6068442 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.7806. Min Act: -0.1629

Data Index: 4479082 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.7626. Min Act: -0.1700

Data Index: 1477620 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.7538. Min Act: -0.1698

Data Index: 1477618 (Open Web Text)

Max Activating Token Index: 88

Text #16

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.7589. Min Act: -0.1616

Data Index: 6068439 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.7382. Min Act: -0.1609

Data Index: 1477628 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.7374. Min Act: -0.1638

Data Index: 4479102 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 4.2686. Min Range: -4.2686

Max Act: 3.7424. Min Act: -0.1696

Data Index: 1477588 (Open Web Text)

Max Activating Token Index: 50