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

Dataset: Open Web Text

Neuron 191 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: 1.6882. Min Range: -1.6882

Max Act: 1.6882. Min Act: -0.1697

Data Index: 2082880 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6524. Min Act: -0.1680

Data Index: 8647180 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6496. Min Act: -0.1700

Data Index: 8058001 (Open Web Text)

Max Activating Token Index: 372

Text #3

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6469. Min Act: -0.1698

Data Index: 513918 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6493. Min Act: -0.1700

Data Index: 6728995 (Open Web Text)

Max Activating Token Index: 259

Text #5

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6504. Min Act: -0.1700

Data Index: 6212631 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6428. Min Act: -0.1661

Data Index: 4682921 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6438. Min Act: -0.1700

Data Index: 8712618 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6408. Min Act: -0.1700

Data Index: 233496 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6466. Min Act: -0.1698

Data Index: 4414545 (Open Web Text)

Max Activating Token Index: 615

Text #10

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6349. Min Act: -0.1692

Data Index: 5890389 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6329. Min Act: -0.1689

Data Index: 6690363 (Open Web Text)

Max Activating Token Index: 649

Text #12

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6242. Min Act: -0.1693

Data Index: 3010547 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6296. Min Act: -0.1700

Data Index: 3855988 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6348. Min Act: -0.1700

Data Index: 7510590 (Open Web Text)

Max Activating Token Index: 394

Text #15

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6221. Min Act: -0.1700

Data Index: 5927710 (Open Web Text)

Max Activating Token Index: 667

Text #16

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6264. Min Act: -0.1613

Data Index: 3764350 (Open Web Text)

Max Activating Token Index: 435

Text #17

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6147. Min Act: -0.1688

Data Index: 4456555 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6083. Min Act: -0.1675

Data Index: 2306152 (Open Web Text)

Max Activating Token Index: 353

Text #19

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6128. Min Act: -0.1700

Data Index: 3616597 (Open Web Text)

Max Activating Token Index: 434