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

Dataset: Open Web Text

Neuron 919 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: 4.7447. Min Range: -4.7447

Max Act: 4.7447. Min Act: -0.1700

Data Index: 6788537 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.7328. Min Act: -0.1700

Data Index: 1031607 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.6084. Min Act: -0.1700

Data Index: 1279485 (Open Web Text)

Max Activating Token Index: 645

Text #3

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5919. Min Act: -0.1700

Data Index: 6751505 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5987. Min Act: -0.1700

Data Index: 5836265 (Open Web Text)

Max Activating Token Index: 813

Text #5

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5797. Min Act: -0.1700

Data Index: 7257723 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.6170. Min Act: -0.1700

Data Index: 106038 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5731. Min Act: -0.1700

Data Index: 7756133 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5465. Min Act: -0.1700

Data Index: 763119 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5990. Min Act: -0.1700

Data Index: 7960425 (Open Web Text)

Max Activating Token Index: 108

Text #10

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5710. Min Act: -0.1700

Data Index: 1583049 (Open Web Text)

Max Activating Token Index: 937

Text #11

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5709. Min Act: -0.1700

Data Index: 2881856 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5337. Min Act: -0.1700

Data Index: 5316556 (Open Web Text)

Max Activating Token Index: 410

Text #13

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5657. Min Act: -0.1700

Data Index: 5778075 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5150. Min Act: -0.1700

Data Index: 707145 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5310. Min Act: -0.1700

Data Index: 4435865 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5613. Min Act: -0.1700

Data Index: 224204 (Open Web Text)

Max Activating Token Index: 361

Text #17

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.5397. Min Act: -0.1700

Data Index: 1627336 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.4594. Min Act: -0.1700

Data Index: 968841 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 4.7447. Min Range: -4.7447

Max Act: 4.4927. Min Act: -0.1700

Data Index: 2587373 (Open Web Text)

Max Activating Token Index: 797