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

Dataset: Open Web Text

Neuron 490 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: 1.0341. Min Range: -1.0341

Max Act: 1.0341. Min Act: -0.1344

Data Index: 4020317 (Open Web Text)

Max Activating Token Index: 371

Text #1

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0219. Min Act: -0.1455

Data Index: 8493555 (Open Web Text)

Max Activating Token Index: 909

Text #2

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0206. Min Act: -0.1420

Data Index: 846729 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0117. Min Act: -0.1504

Data Index: 1349896 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0109. Min Act: -0.1451

Data Index: 6446221 (Open Web Text)

Max Activating Token Index: 826

Text #5

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0016. Min Act: -0.1301

Data Index: 2201731 (Open Web Text)

Max Activating Token Index: 953

Text #6

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0066. Min Act: -0.1366

Data Index: 689400 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9842. Min Act: -0.1625

Data Index: 8449310 (Open Web Text)

Max Activating Token Index: 801

Text #8

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9908. Min Act: -0.1632

Data Index: 2923578 (Open Web Text)

Max Activating Token Index: 886

Text #9

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9796. Min Act: -0.1412

Data Index: 517053 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9775. Min Act: -0.1274

Data Index: 5624522 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9783. Min Act: -0.1589

Data Index: 1308494 (Open Web Text)

Max Activating Token Index: 386

Text #12

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9824. Min Act: -0.1530

Data Index: 3923258 (Open Web Text)

Max Activating Token Index: 724

Text #13

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9732. Min Act: -0.1152

Data Index: 3085020 (Open Web Text)

Max Activating Token Index: 824

Text #14

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9767. Min Act: -0.1143

Data Index: 8107683 (Open Web Text)

Max Activating Token Index: 831

Text #15

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9732. Min Act: -0.1480

Data Index: 5236874 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9724. Min Act: -0.1484

Data Index: 821015 (Open Web Text)

Max Activating Token Index: 902

Text #17

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9669. Min Act: -0.1410

Data Index: 327090 (Open Web Text)

Max Activating Token Index: 851

Text #18

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9676. Min Act: -0.1582

Data Index: 6280367 (Open Web Text)

Max Activating Token Index: 910

Text #19

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9673. Min Act: -0.1570

Data Index: 197929 (Open Web Text)

Max Activating Token Index: 280