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

Dataset: Open Web Text

Neuron 765 in Layer 1

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: 1.4273. Min Range: -1.4273

Max Act: 1.4273. Min Act: -0.1546

Data Index: 2645176 (Open Web Text)

Max Activating Token Index: 952

Text #1

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3835. Min Act: -0.1668

Data Index: 3704963 (Open Web Text)

Max Activating Token Index: 216

Text #2

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3765. Min Act: -0.1694

Data Index: 8137615 (Open Web Text)

Max Activating Token Index: 851

Text #3

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3809. Min Act: -0.1677

Data Index: 4253246 (Open Web Text)

Max Activating Token Index: 291

Text #4

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3748. Min Act: -0.1700

Data Index: 663160 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3680. Min Act: -0.1690

Data Index: 1912429 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3663. Min Act: -0.1699

Data Index: 4368217 (Open Web Text)

Max Activating Token Index: 289

Text #7

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3664. Min Act: -0.1697

Data Index: 6800604 (Open Web Text)

Max Activating Token Index: 722

Text #8

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3610. Min Act: -0.1699

Data Index: 663962 (Open Web Text)

Max Activating Token Index: 319

Text #9

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3680. Min Act: -0.1650

Data Index: 4225063 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3607. Min Act: -0.1698

Data Index: 4793825 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3509. Min Act: -0.1699

Data Index: 6460201 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3576. Min Act: -0.1700

Data Index: 2708863 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3645. Min Act: -0.1689

Data Index: 5522670 (Open Web Text)

Max Activating Token Index: 311

Text #14

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3570. Min Act: -0.1697

Data Index: 4524765 (Open Web Text)

Max Activating Token Index: 933

Text #15

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3521. Min Act: -0.1585

Data Index: 6366257 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3443. Min Act: -0.1679

Data Index: 415537 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3476. Min Act: -0.1700

Data Index: 6407740 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3433. Min Act: -0.1698

Data Index: 2744361 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 1.4273. Min Range: -1.4273

Max Act: 1.3512. Min Act: -0.1685

Data Index: 5164400 (Open Web Text)

Max Activating Token Index: 825