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

Dataset: Open Web Text

Neuron 2665 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: 1.8035. Min Range: -1.8035

Max Act: 1.8035. Min Act: -0.1700

Data Index: 8794602 (Open Web Text)

Max Activating Token Index: 429

Text #1

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7495. Min Act: -0.1700

Data Index: 4544334 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7107. Min Act: -0.1700

Data Index: 7771726 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.7047. Min Act: -0.1700

Data Index: 1340540 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6906. Min Act: -0.1700

Data Index: 8697478 (Open Web Text)

Max Activating Token Index: 371

Text #5

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6968. Min Act: -0.1700

Data Index: 722029 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6719. Min Act: -0.1700

Data Index: 185412 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6917. Min Act: -0.1700

Data Index: 4319806 (Open Web Text)

Max Activating Token Index: 382

Text #8

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6784. Min Act: -0.1700

Data Index: 58447 (Open Web Text)

Max Activating Token Index: 368

Text #9

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6773. Min Act: -0.1700

Data Index: 8426755 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6770. Min Act: -0.1700

Data Index: 2985546 (Open Web Text)

Max Activating Token Index: 428

Text #11

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6811. Min Act: -0.1700

Data Index: 8720655 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6611. Min Act: -0.1700

Data Index: 5748289 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6717. Min Act: -0.1700

Data Index: 2540167 (Open Web Text)

Max Activating Token Index: 383

Text #14

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6714. Min Act: -0.1700

Data Index: 583710 (Open Web Text)

Max Activating Token Index: 417

Text #15

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6558. Min Act: -0.1700

Data Index: 1718148 (Open Web Text)

Max Activating Token Index: 378

Text #16

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6458. Min Act: -0.1700

Data Index: 6076782 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6416. Min Act: -0.1700

Data Index: 5803134 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6452. Min Act: -0.1700

Data Index: 1000647 (Open Web Text)

Max Activating Token Index: 419

Text #19

Max Range: 1.8035. Min Range: -1.8035

Max Act: 1.6457. Min Act: -0.1700

Data Index: 5145617 (Open Web Text)

Max Activating Token Index: 392