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

Dataset: Open Web Text

Neuron 1180 in Layer 5

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: 2.6289. Min Range: -2.6289

Max Act: 2.6289. Min Act: -0.1700

Data Index: 415609 (Open Web Text)

Max Activating Token Index: 610

Text #1

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.6084. Min Act: -0.1700

Data Index: 975183 (Open Web Text)

Max Activating Token Index: 829

Text #2

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5778. Min Act: -0.1698

Data Index: 7460756 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5698. Min Act: -0.1690

Data Index: 2653299 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5514. Min Act: -0.1696

Data Index: 3865118 (Open Web Text)

Max Activating Token Index: 582

Text #5

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5617. Min Act: -0.1700

Data Index: 2207104 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5405. Min Act: -0.1700

Data Index: 7204213 (Open Web Text)

Max Activating Token Index: 829

Text #7

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5413. Min Act: -0.1698

Data Index: 3865117 (Open Web Text)

Max Activating Token Index: 732

Text #8

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5389. Min Act: -0.1699

Data Index: 367063 (Open Web Text)

Max Activating Token Index: 381

Text #9

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5320. Min Act: -0.1699

Data Index: 4968822 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5441. Min Act: -0.1694

Data Index: 5329571 (Open Web Text)

Max Activating Token Index: 617

Text #11

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5175. Min Act: -0.1700

Data Index: 6803111 (Open Web Text)

Max Activating Token Index: 714

Text #12

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5025. Min Act: -0.1700

Data Index: 3303225 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.4995. Min Act: -0.1700

Data Index: 1115129 (Open Web Text)

Max Activating Token Index: 735

Text #14

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5248. Min Act: -0.1693

Data Index: 854129 (Open Web Text)

Max Activating Token Index: 561

Text #15

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5077. Min Act: -0.1700

Data Index: 596325 (Open Web Text)

Max Activating Token Index: 604

Text #16

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5294. Min Act: -0.1700

Data Index: 2685267 (Open Web Text)

Max Activating Token Index: 729

Text #17

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.5186. Min Act: -0.1694

Data Index: 4096691 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.4972. Min Act: -0.1674

Data Index: 7918775 (Open Web Text)

Max Activating Token Index: 551

Text #19

Max Range: 2.6289. Min Range: -2.6289

Max Act: 2.4796. Min Act: -0.1692

Data Index: 2014862 (Open Web Text)

Max Activating Token Index: 307