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

Dataset: Open Web Text

Neuron 2922 in Layer 0

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: 1.5517. Min Range: -1.5517

Max Act: 1.5517. Min Act: -0.1699

Data Index: 7529450 (Open Web Text)

Max Activating Token Index: 362

Text #1

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5324. Min Act: -0.1560

Data Index: 2255271 (Open Web Text)

Max Activating Token Index: 738

Text #2

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5243. Min Act: -0.1626

Data Index: 2249828 (Open Web Text)

Max Activating Token Index: 387

Text #3

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5193. Min Act: -0.1664

Data Index: 1323408 (Open Web Text)

Max Activating Token Index: 890

Text #4

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5029. Min Act: -0.1685

Data Index: 6131447 (Open Web Text)

Max Activating Token Index: 790

Text #5

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5086. Min Act: -0.1398

Data Index: 4288582 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.5183. Min Act: -0.1669

Data Index: 4521561 (Open Web Text)

Max Activating Token Index: 551

Text #7

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4922. Min Act: -0.1628

Data Index: 3331486 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4764. Min Act: -0.1684

Data Index: 5816858 (Open Web Text)

Max Activating Token Index: 109

Text #9

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4780. Min Act: -0.1450

Data Index: 2567822 (Open Web Text)

Max Activating Token Index: 791

Text #10

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4553. Min Act: -0.1436

Data Index: 5372874 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4591. Min Act: -0.1696

Data Index: 5121854 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4504. Min Act: -0.1675

Data Index: 2286763 (Open Web Text)

Max Activating Token Index: 878

Text #13

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4500. Min Act: -0.1676

Data Index: 5524511 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4470. Min Act: -0.1584

Data Index: 1824785 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4478. Min Act: -0.1536

Data Index: 2285604 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4397. Min Act: -0.1486

Data Index: 4066718 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4381. Min Act: -0.1577

Data Index: 7583867 (Open Web Text)

Max Activating Token Index: 598

Text #18

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4358. Min Act: -0.1695

Data Index: 8455442 (Open Web Text)

Max Activating Token Index: 297

Text #19

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.4425. Min Act: -0.1529

Data Index: 995477 (Open Web Text)

Max Activating Token Index: 696