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

Dataset: Open Web Text

Neuron 1619 in Layer 2

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: 2.7216. Min Range: -2.7216

Max Act: 2.7216. Min Act: -0.1700

Data Index: 5352682 (Open Web Text)

Max Activating Token Index: 28

Text #1

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.7212. Min Act: -0.1700

Data Index: 8413985 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6931. Min Act: -0.1700

Data Index: 1958654 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6689. Min Act: -0.1700

Data Index: 3644762 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6227. Min Act: -0.1700

Data Index: 2746614 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6192. Min Act: -0.1700

Data Index: 3446903 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6101. Min Act: -0.1700

Data Index: 5189102 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6401. Min Act: -0.1700

Data Index: 7870535 (Open Web Text)

Max Activating Token Index: 658

Text #8

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5938. Min Act: -0.1700

Data Index: 3893689 (Open Web Text)

Max Activating Token Index: 942

Text #9

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6146. Min Act: -0.1700

Data Index: 7616893 (Open Web Text)

Max Activating Token Index: 300

Text #10

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.6085. Min Act: -0.1700

Data Index: 5490722 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5982. Min Act: -0.1700

Data Index: 5234426 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5858. Min Act: -0.1700

Data Index: 345757 (Open Web Text)

Max Activating Token Index: 479

Text #13

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5840. Min Act: -0.1700

Data Index: 8073853 (Open Web Text)

Max Activating Token Index: 964

Text #14

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5967. Min Act: -0.1700

Data Index: 5948431 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5866. Min Act: -0.1700

Data Index: 7976354 (Open Web Text)

Max Activating Token Index: 147

Text #16

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5692. Min Act: -0.1700

Data Index: 7504984 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5722. Min Act: -0.1700

Data Index: 1715145 (Open Web Text)

Max Activating Token Index: 725

Text #18

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5719. Min Act: -0.1700

Data Index: 764634 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 2.7216. Min Range: -2.7216

Max Act: 2.5699. Min Act: -0.1700

Data Index: 1268313 (Open Web Text)

Max Activating Token Index: 523