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

Dataset: Open Web Text

Neuron 1938 in Layer 1

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: 0.8025. Min Range: -0.8025

Max Act: 0.8025. Min Act: -0.1700

Data Index: 8328508 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7914. Min Act: -0.1700

Data Index: 4594574 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7683. Min Act: -0.1700

Data Index: 5259021 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7603. Min Act: -0.1700

Data Index: 4117433 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7624. Min Act: -0.1700

Data Index: 299941 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7524. Min Act: -0.1700

Data Index: 5259020 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7546. Min Act: -0.1700

Data Index: 6694735 (Open Web Text)

Max Activating Token Index: 358

Text #7

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7448. Min Act: -0.1700

Data Index: 5567891 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7411. Min Act: -0.1700

Data Index: 877255 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7408. Min Act: -0.1700

Data Index: 5390695 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7336. Min Act: -0.1700

Data Index: 6004981 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7324. Min Act: -0.1700

Data Index: 6694722 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7283. Min Act: -0.1700

Data Index: 2699378 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7348. Min Act: -0.1700

Data Index: 3393661 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7253. Min Act: -0.1700

Data Index: 2835088 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7267. Min Act: -0.1700

Data Index: 4585626 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7160. Min Act: -0.1700

Data Index: 5304011 (Open Web Text)

Max Activating Token Index: 360

Text #17

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7143. Min Act: -0.1700

Data Index: 3705856 (Open Web Text)

Max Activating Token Index: 378

Text #18

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7161. Min Act: -0.1700

Data Index: 3969467 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 0.8025. Min Range: -0.8025

Max Act: 0.7197. Min Act: -0.1700

Data Index: 5553882 (Open Web Text)

Max Activating Token Index: 387