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

Dataset: Open Web Text

Neuron 909 in Layer 6

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: 5.5688. Min Range: -5.5688

Max Act: 5.5688. Min Act: -0.1700

Data Index: 5508372 (Open Web Text)

Max Activating Token Index: 587

Text #1

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.5021. Min Act: -0.1700

Data Index: 3890058 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.3879. Min Act: -0.1700

Data Index: 7406741 (Open Web Text)

Max Activating Token Index: 448

Text #3

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.3386. Min Act: -0.1700

Data Index: 4102343 (Open Web Text)

Max Activating Token Index: 1011

Text #4

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.2844. Min Act: -0.1700

Data Index: 2775803 (Open Web Text)

Max Activating Token Index: 765

Text #5

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.2476. Min Act: -0.1700

Data Index: 248592 (Open Web Text)

Max Activating Token Index: 1006

Text #6

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.2447. Min Act: -0.1700

Data Index: 6136754 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.2000. Min Act: -0.1700

Data Index: 8274858 (Open Web Text)

Max Activating Token Index: 709

Text #8

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1736. Min Act: -0.1700

Data Index: 4441802 (Open Web Text)

Max Activating Token Index: 340

Text #9

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1741. Min Act: -0.1700

Data Index: 4419748 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1313. Min Act: -0.1700

Data Index: 3678023 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1919. Min Act: -0.1700

Data Index: 1030182 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.0666. Min Act: -0.1700

Data Index: 5327546 (Open Web Text)

Max Activating Token Index: 739

Text #13

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1637. Min Act: -0.1700

Data Index: 988997 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1051. Min Act: -0.1700

Data Index: 8507861 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.0774. Min Act: -0.1700

Data Index: 5556621 (Open Web Text)

Max Activating Token Index: 529

Text #16

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1087. Min Act: -0.1700

Data Index: 289665 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.1113. Min Act: -0.1700

Data Index: 7311219 (Open Web Text)

Max Activating Token Index: 733

Text #18

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.0941. Min Act: -0.1700

Data Index: 3302131 (Open Web Text)

Max Activating Token Index: 899

Text #19

Max Range: 5.5688. Min Range: -5.5688

Max Act: 5.0705. Min Act: -0.1700

Data Index: 2157434 (Open Web Text)

Max Activating Token Index: 651