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

Dataset: Open Web Text

Neuron 2460 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: 1.8325. Min Range: -1.8325

Max Act: 1.8325. Min Act: -0.1230

Data Index: 5531031 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.8012. Min Act: -0.1599

Data Index: 5061708 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7863. Min Act: -0.1382

Data Index: 5366437 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7870. Min Act: -0.0744

Data Index: 695664 (Open Web Text)

Max Activating Token Index: 768

Text #4

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7731. Min Act: -0.1582

Data Index: 7430393 (Open Web Text)

Max Activating Token Index: 486

Text #5

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7762. Min Act: -0.1636

Data Index: 3879370 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7684. Min Act: -0.1556

Data Index: 8629340 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7716. Min Act: -0.1621

Data Index: 2708224 (Open Web Text)

Max Activating Token Index: 278

Text #8

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7638. Min Act: -0.1648

Data Index: 6015203 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7639. Min Act: -0.1660

Data Index: 5290145 (Open Web Text)

Max Activating Token Index: 1020

Text #10

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7609. Min Act: -0.1684

Data Index: 6597317 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7583. Min Act: -0.1585

Data Index: 5567965 (Open Web Text)

Max Activating Token Index: 467

Text #12

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7611. Min Act: -0.1492

Data Index: 5226012 (Open Web Text)

Max Activating Token Index: 160

Text #13

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7585. Min Act: -0.1698

Data Index: 5061707 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7555. Min Act: -0.1428

Data Index: 8069190 (Open Web Text)

Max Activating Token Index: 718

Text #15

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7381. Min Act: -0.1657

Data Index: 6015202 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7447. Min Act: -0.1667

Data Index: 8569003 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7507. Min Act: -0.1700

Data Index: 5717443 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7540. Min Act: -0.1612

Data Index: 6316471 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 1.8325. Min Range: -1.8325

Max Act: 1.7384. Min Act: -0.1344

Data Index: 2879928 (Open Web Text)

Max Activating Token Index: 365