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

Dataset: Open Web Text

Neuron 3031 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: 4.9811. Min Range: -4.9811

Max Act: 4.9811. Min Act: -0.1700

Data Index: 6797119 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.6681. Min Act: -0.1700

Data Index: 1994708 (Open Web Text)

Max Activating Token Index: 778

Text #2

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.6417. Min Act: -0.1700

Data Index: 2213143 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.6269. Min Act: -0.1700

Data Index: 1627265 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.6161. Min Act: -0.1700

Data Index: 6941930 (Open Web Text)

Max Activating Token Index: 272

Text #5

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.6143. Min Act: -0.1700

Data Index: 7764794 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.6116. Min Act: -0.1700

Data Index: 3400805 (Open Web Text)

Max Activating Token Index: 443

Text #7

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5602. Min Act: -0.1700

Data Index: 6248055 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5336. Min Act: -0.1700

Data Index: 7899941 (Open Web Text)

Max Activating Token Index: 914

Text #9

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5295. Min Act: -0.1700

Data Index: 2872171 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5560. Min Act: -0.1700

Data Index: 3365973 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5521. Min Act: -0.1700

Data Index: 3691323 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5446. Min Act: -0.1700

Data Index: 2662112 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5462. Min Act: -0.1700

Data Index: 3014780 (Open Web Text)

Max Activating Token Index: 841

Text #14

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5437. Min Act: -0.1700

Data Index: 414501 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5238. Min Act: -0.1700

Data Index: 3166348 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5305. Min Act: -0.1700

Data Index: 4952801 (Open Web Text)

Max Activating Token Index: 232

Text #17

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5153. Min Act: -0.1700

Data Index: 5596347 (Open Web Text)

Max Activating Token Index: 750

Text #18

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5165. Min Act: -0.1700

Data Index: 5591100 (Open Web Text)

Max Activating Token Index: 457

Text #19

Max Range: 4.9811. Min Range: -4.9811

Max Act: 4.5086. Min Act: -0.1700

Data Index: 2441378 (Open Web Text)

Max Activating Token Index: 750