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

Dataset: Open Web Text

Neuron 2931 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: 3.2237. Min Range: -3.2237

Max Act: 3.2214. Min Act: -0.1700

Data Index: 4228384 (Open Web Text)

Max Activating Token Index: 521

Text #1

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.2237. Min Act: -0.1700

Data Index: 8320761 (Open Web Text)

Max Activating Token Index: 504

Text #2

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1764. Min Act: -0.1700

Data Index: 8593907 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1878. Min Act: -0.1700

Data Index: 4456068 (Open Web Text)

Max Activating Token Index: 517

Text #4

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1814. Min Act: -0.1700

Data Index: 2892039 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1599. Min Act: -0.1700

Data Index: 2224642 (Open Web Text)

Max Activating Token Index: 886

Text #6

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1712. Min Act: -0.1700

Data Index: 8027170 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1538. Min Act: -0.1700

Data Index: 6292343 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1482. Min Act: -0.1700

Data Index: 8707807 (Open Web Text)

Max Activating Token Index: 928

Text #9

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1420. Min Act: -0.1700

Data Index: 7290728 (Open Web Text)

Max Activating Token Index: 594

Text #10

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1653. Min Act: -0.1700

Data Index: 7931076 (Open Web Text)

Max Activating Token Index: 596

Text #11

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1390. Min Act: -0.1700

Data Index: 3068337 (Open Web Text)

Max Activating Token Index: 697

Text #12

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1558. Min Act: -0.1700

Data Index: 2994595 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1300. Min Act: -0.1700

Data Index: 6316417 (Open Web Text)

Max Activating Token Index: 328

Text #14

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1624. Min Act: -0.1700

Data Index: 1641284 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1402. Min Act: -0.1700

Data Index: 7759415 (Open Web Text)

Max Activating Token Index: 685

Text #16

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1276. Min Act: -0.1700

Data Index: 8365337 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1248. Min Act: -0.1700

Data Index: 1412548 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1173. Min Act: -0.1700

Data Index: 8282679 (Open Web Text)

Max Activating Token Index: 541

Text #19

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1265. Min Act: -0.1700

Data Index: 2370434 (Open Web Text)

Max Activating Token Index: 68