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

Dataset: Open Web Text

Neuron 532 in Layer 1

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: 4.8765. Min Range: -4.8765

Max Act: 4.8765. Min Act: -0.1700

Data Index: 6973839 (Open Web Text)

Max Activating Token Index: 519

Text #1

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8559. Min Act: -0.1700

Data Index: 797602 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8513. Min Act: -0.1700

Data Index: 6772503 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8657. Min Act: -0.1700

Data Index: 6772506 (Open Web Text)

Max Activating Token Index: 140

Text #4

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8304. Min Act: -0.1700

Data Index: 6543798 (Open Web Text)

Max Activating Token Index: 424

Text #5

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8006. Min Act: -0.1700

Data Index: 3566665 (Open Web Text)

Max Activating Token Index: 250

Text #6

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7987. Min Act: -0.1700

Data Index: 4657361 (Open Web Text)

Max Activating Token Index: 925

Text #7

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7974. Min Act: -0.1700

Data Index: 3711505 (Open Web Text)

Max Activating Token Index: 260

Text #8

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7976. Min Act: -0.1700

Data Index: 2181359 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7978. Min Act: -0.1700

Data Index: 5793366 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.8020. Min Act: -0.1700

Data Index: 5608330 (Open Web Text)

Max Activating Token Index: 239

Text #11

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7867. Min Act: -0.1700

Data Index: 5423227 (Open Web Text)

Max Activating Token Index: 329

Text #12

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7624. Min Act: -0.1700

Data Index: 482953 (Open Web Text)

Max Activating Token Index: 678

Text #13

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7773. Min Act: -0.1700

Data Index: 3341806 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7636. Min Act: -0.1700

Data Index: 1845544 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7609. Min Act: -0.1700

Data Index: 4008512 (Open Web Text)

Max Activating Token Index: 306

Text #16

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7645. Min Act: -0.1700

Data Index: 537735 (Open Web Text)

Max Activating Token Index: 389

Text #17

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7792. Min Act: -0.1700

Data Index: 4273474 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7569. Min Act: -0.1700

Data Index: 4639696 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 4.8765. Min Range: -4.8765

Max Act: 4.7779. Min Act: -0.1700

Data Index: 931521 (Open Web Text)

Max Activating Token Index: 199