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

Dataset: Open Web Text

Neuron 2446 in Layer 4

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: 4.3693. Min Range: -4.3693

Max Act: 4.3693. Min Act: -0.1700

Data Index: 7937358 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.3582. Min Act: -0.1700

Data Index: 871097 (Open Web Text)

Max Activating Token Index: 967

Text #2

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.3273. Min Act: -0.1700

Data Index: 5832271 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1841. Min Act: -0.1700

Data Index: 4696197 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.2050. Min Act: -0.1700

Data Index: 8085454 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1509. Min Act: -0.1700

Data Index: 8271516 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1269. Min Act: -0.1700

Data Index: 1958247 (Open Web Text)

Max Activating Token Index: 511

Text #7

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1496. Min Act: -0.1700

Data Index: 2500003 (Open Web Text)

Max Activating Token Index: 86

Text #8

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1809. Min Act: -0.1700

Data Index: 3431437 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1576. Min Act: -0.1700

Data Index: 118951 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1517. Min Act: -0.1700

Data Index: 1118437 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1603. Min Act: -0.1700

Data Index: 6548429 (Open Web Text)

Max Activating Token Index: 648

Text #12

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1355. Min Act: -0.1700

Data Index: 7535107 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.0903. Min Act: -0.1700

Data Index: 4199196 (Open Web Text)

Max Activating Token Index: 846

Text #14

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1716. Min Act: -0.1700

Data Index: 161264 (Open Web Text)

Max Activating Token Index: 889

Text #15

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1122. Min Act: -0.1700

Data Index: 7435583 (Open Web Text)

Max Activating Token Index: 369

Text #16

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1436. Min Act: -0.1700

Data Index: 2331675 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.0957. Min Act: -0.1700

Data Index: 1603960 (Open Web Text)

Max Activating Token Index: 430

Text #18

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1401. Min Act: -0.1700

Data Index: 888885 (Open Web Text)

Max Activating Token Index: 302

Text #19

Max Range: 4.3693. Min Range: -4.3693

Max Act: 4.1032. Min Act: -0.1700

Data Index: 169878 (Open Web Text)

Max Activating Token Index: 697