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

Dataset: Open Web Text

Neuron 1478 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: 4.5495. Min Range: -4.5495

Max Act: 4.5495. Min Act: -0.1700

Data Index: 2502063 (Open Web Text)

Max Activating Token Index: 927

Text #1

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4960. Min Act: -0.1700

Data Index: 1698935 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.5367. Min Act: -0.1700

Data Index: 5245113 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.5096. Min Act: -0.1700

Data Index: 8724836 (Open Web Text)

Max Activating Token Index: 721

Text #4

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4799. Min Act: -0.1700

Data Index: 4050669 (Open Web Text)

Max Activating Token Index: 454

Text #5

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4583. Min Act: -0.1700

Data Index: 5815335 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4776. Min Act: -0.1700

Data Index: 4847831 (Open Web Text)

Max Activating Token Index: 723

Text #7

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4819. Min Act: -0.1700

Data Index: 4544875 (Open Web Text)

Max Activating Token Index: 327

Text #8

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4597. Min Act: -0.1700

Data Index: 8605936 (Open Web Text)

Max Activating Token Index: 534

Text #9

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4225. Min Act: -0.1700

Data Index: 3817995 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4007. Min Act: -0.1700

Data Index: 1229213 (Open Web Text)

Max Activating Token Index: 593

Text #11

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4060. Min Act: -0.1700

Data Index: 755842 (Open Web Text)

Max Activating Token Index: 764

Text #12

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4234. Min Act: -0.1700

Data Index: 7126150 (Open Web Text)

Max Activating Token Index: 211

Text #13

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.4042. Min Act: -0.1700

Data Index: 1522398 (Open Web Text)

Max Activating Token Index: 416

Text #14

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3981. Min Act: -0.1700

Data Index: 5487237 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3617. Min Act: -0.1700

Data Index: 7094229 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3839. Min Act: -0.1700

Data Index: 6026901 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3754. Min Act: -0.1700

Data Index: 8796082 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3613. Min Act: -0.1700

Data Index: 3248646 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 4.5495. Min Range: -4.5495

Max Act: 4.3511. Min Act: -0.1700

Data Index: 5247533 (Open Web Text)

Max Activating Token Index: 702