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

Dataset: Open Web Text

Neuron 1369 in Layer 2

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: 4.2137. Min Range: -4.2137

Max Act: 4.1932. Min Act: -0.1700

Data Index: 5963699 (Open Web Text)

Max Activating Token Index: 566

Text #1

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.2002. Min Act: -0.1700

Data Index: 4711246 (Open Web Text)

Max Activating Token Index: 909

Text #2

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.2137. Min Act: -0.1700

Data Index: 661365 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.2031. Min Act: -0.1700

Data Index: 2594469 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1699. Min Act: -0.1700

Data Index: 6284222 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1847. Min Act: -0.1700

Data Index: 6507423 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1918. Min Act: -0.1699

Data Index: 6676666 (Open Web Text)

Max Activating Token Index: 246

Text #7

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1687. Min Act: -0.1700

Data Index: 1618753 (Open Web Text)

Max Activating Token Index: 590

Text #8

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1997. Min Act: -0.1700

Data Index: 6749457 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1807. Min Act: -0.1700

Data Index: 3896491 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1618. Min Act: -0.1700

Data Index: 7618468 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1705. Min Act: -0.1700

Data Index: 4993016 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1496. Min Act: -0.1700

Data Index: 5796199 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1606. Min Act: -0.1700

Data Index: 62693 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1465. Min Act: -0.1700

Data Index: 5504191 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1584. Min Act: -0.1700

Data Index: 406292 (Open Web Text)

Max Activating Token Index: 963

Text #16

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1429. Min Act: -0.1700

Data Index: 2585709 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1361. Min Act: -0.1698

Data Index: 1049230 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1499. Min Act: -0.1700

Data Index: 4972228 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 4.2137. Min Range: -4.2137

Max Act: 4.1456. Min Act: -0.1700

Data Index: 384156 (Open Web Text)

Max Activating Token Index: 809