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

Dataset: Open Web Text

Neuron 2221 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: 4.1473. Min Range: -4.1473

Max Act: 4.1473. Min Act: -0.1700

Data Index: 659917 (Open Web Text)

Max Activating Token Index: 280

Text #1

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.1043. Min Act: -0.1700

Data Index: 3401123 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0967. Min Act: -0.1700

Data Index: 4900081 (Open Web Text)

Max Activating Token Index: 327

Text #3

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0959. Min Act: -0.1700

Data Index: 7519359 (Open Web Text)

Max Activating Token Index: 623

Text #4

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0833. Min Act: -0.1700

Data Index: 680697 (Open Web Text)

Max Activating Token Index: 240

Text #5

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0300. Min Act: -0.1700

Data Index: 6288899 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0571. Min Act: -0.1700

Data Index: 6138564 (Open Web Text)

Max Activating Token Index: 332

Text #7

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0413. Min Act: -0.1700

Data Index: 3019485 (Open Web Text)

Max Activating Token Index: 160

Text #8

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0409. Min Act: -0.1700

Data Index: 1764687 (Open Web Text)

Max Activating Token Index: 650

Text #9

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0233. Min Act: -0.1700

Data Index: 6383263 (Open Web Text)

Max Activating Token Index: 497

Text #10

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0057. Min Act: -0.1700

Data Index: 4017454 (Open Web Text)

Max Activating Token Index: 516

Text #11

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0195. Min Act: -0.1700

Data Index: 5207283 (Open Web Text)

Max Activating Token Index: 74

Text #12

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0141. Min Act: -0.1700

Data Index: 5058812 (Open Web Text)

Max Activating Token Index: 697

Text #13

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0025. Min Act: -0.1700

Data Index: 3232785 (Open Web Text)

Max Activating Token Index: 523

Text #14

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0125. Min Act: -0.1700

Data Index: 7217038 (Open Web Text)

Max Activating Token Index: 455

Text #15

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0183. Min Act: -0.1700

Data Index: 6656804 (Open Web Text)

Max Activating Token Index: 848

Text #16

Max Range: 4.1473. Min Range: -4.1473

Max Act: 4.0263. Min Act: -0.1700

Data Index: 2477689 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 4.1473. Min Range: -4.1473

Max Act: 3.9885. Min Act: -0.1700

Data Index: 1774414 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 4.1473. Min Range: -4.1473

Max Act: 3.9837. Min Act: -0.1700

Data Index: 2324754 (Open Web Text)

Max Activating Token Index: 707

Text #19

Max Range: 4.1473. Min Range: -4.1473

Max Act: 3.9754. Min Act: -0.1700

Data Index: 5412376 (Open Web Text)

Max Activating Token Index: 110