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

Dataset: Open Web Text

Neuron 1519 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: 4.1889. Min Range: -4.1889

Max Act: 4.1889. Min Act: -0.1700

Data Index: 7486034 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.1059. Min Act: -0.1700

Data Index: 7858620 (Open Web Text)

Max Activating Token Index: 913

Text #2

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0128. Min Act: -0.1700

Data Index: 2294283 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 4.1889. Min Range: -4.1889

Max Act: 4.0178. Min Act: -0.1700

Data Index: 970061 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9639. Min Act: -0.1700

Data Index: 5156866 (Open Web Text)

Max Activating Token Index: 402

Text #5

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9752. Min Act: -0.1700

Data Index: 7530092 (Open Web Text)

Max Activating Token Index: 147

Text #6

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9606. Min Act: -0.1700

Data Index: 6937209 (Open Web Text)

Max Activating Token Index: 862

Text #7

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9264. Min Act: -0.1700

Data Index: 800387 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9334. Min Act: -0.1700

Data Index: 6095723 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9362. Min Act: -0.1700

Data Index: 7769198 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8896. Min Act: -0.1700

Data Index: 7414645 (Open Web Text)

Max Activating Token Index: 370

Text #11

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9080. Min Act: -0.1700

Data Index: 5433665 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8863. Min Act: -0.1700

Data Index: 7572375 (Open Web Text)

Max Activating Token Index: 820

Text #13

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9027. Min Act: -0.1700

Data Index: 3659256 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8908. Min Act: -0.1700

Data Index: 6647773 (Open Web Text)

Max Activating Token Index: 565

Text #15

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8618. Min Act: -0.1700

Data Index: 6356764 (Open Web Text)

Max Activating Token Index: 345

Text #16

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8654. Min Act: -0.1700

Data Index: 419543 (Open Web Text)

Max Activating Token Index: 378

Text #17

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9024. Min Act: -0.1700

Data Index: 2320489 (Open Web Text)

Max Activating Token Index: 364

Text #18

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.9158. Min Act: -0.1700

Data Index: 3308231 (Open Web Text)

Max Activating Token Index: 591

Text #19

Max Range: 4.1889. Min Range: -4.1889

Max Act: 3.8954. Min Act: -0.1700

Data Index: 7217669 (Open Web Text)

Max Activating Token Index: 663