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

Dataset: Open Web Text

Neuron 399 in Layer 3

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: 4.5682. Min Range: -4.5682

Max Act: 4.5682. Min Act: -0.1700

Data Index: 8426353 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.4313. Min Act: -0.1700

Data Index: 4388034 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.4106. Min Act: -0.1700

Data Index: 5693256 (Open Web Text)

Max Activating Token Index: 693

Text #3

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.3610. Min Act: -0.1700

Data Index: 8648785 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2907. Min Act: -0.1700

Data Index: 4608542 (Open Web Text)

Max Activating Token Index: 179

Text #5

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2399. Min Act: -0.1700

Data Index: 7280979 (Open Web Text)

Max Activating Token Index: 405

Text #6

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2215. Min Act: -0.1700

Data Index: 3106702 (Open Web Text)

Max Activating Token Index: 385

Text #7

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2201. Min Act: -0.1700

Data Index: 2121256 (Open Web Text)

Max Activating Token Index: 165

Text #8

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2398. Min Act: -0.1700

Data Index: 814415 (Open Web Text)

Max Activating Token Index: 80

Text #9

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1970. Min Act: -0.1700

Data Index: 7816422 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.2056. Min Act: -0.1700

Data Index: 814416 (Open Web Text)

Max Activating Token Index: 240

Text #11

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1948. Min Act: -0.1700

Data Index: 6911216 (Open Web Text)

Max Activating Token Index: 107

Text #12

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1696. Min Act: -0.1700

Data Index: 221311 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1455. Min Act: -0.1700

Data Index: 1187512 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1601. Min Act: -0.1700

Data Index: 5788188 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1021. Min Act: -0.1700

Data Index: 3843204 (Open Web Text)

Max Activating Token Index: 137

Text #16

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.0803. Min Act: -0.1700

Data Index: 6957931 (Open Web Text)

Max Activating Token Index: 769

Text #17

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1116. Min Act: -0.1700

Data Index: 6184534 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.1209. Min Act: -0.1700

Data Index: 7765734 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 4.5682. Min Range: -4.5682

Max Act: 4.0852. Min Act: -0.1700

Data Index: 5355453 (Open Web Text)

Max Activating Token Index: 528