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

Dataset: Open Web Text

Neuron 1560 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: 3.5840. Min Range: -3.5840

Max Act: 3.5840. Min Act: -0.1700

Data Index: 8501192 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5592. Min Act: -0.1682

Data Index: 5390769 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5559. Min Act: -0.1700

Data Index: 7181641 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5569. Min Act: -0.1700

Data Index: 2173419 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5695. Min Act: -0.1699

Data Index: 8501196 (Open Web Text)

Max Activating Token Index: 365

Text #5

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5784. Min Act: -0.1698

Data Index: 8501194 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5749. Min Act: -0.1700

Data Index: 8501207 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5652. Min Act: -0.1699

Data Index: 8501205 (Open Web Text)

Max Activating Token Index: 375

Text #8

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5772. Min Act: -0.1700

Data Index: 8748581 (Open Web Text)

Max Activating Token Index: 409

Text #9

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5529. Min Act: -0.1695

Data Index: 2173420 (Open Web Text)

Max Activating Token Index: 857

Text #10

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5476. Min Act: -0.1700

Data Index: 4664863 (Open Web Text)

Max Activating Token Index: 394

Text #11

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5441. Min Act: -0.1700

Data Index: 4391371 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5373. Min Act: -0.1700

Data Index: 839008 (Open Web Text)

Max Activating Token Index: 444

Text #13

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5522. Min Act: -0.1700

Data Index: 3971346 (Open Web Text)

Max Activating Token Index: 649

Text #14

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5305. Min Act: -0.1698

Data Index: 3735221 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5452. Min Act: -0.1682

Data Index: 3735220 (Open Web Text)

Max Activating Token Index: 396

Text #16

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5242. Min Act: -0.1700

Data Index: 3066955 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5105. Min Act: -0.1694

Data Index: 447827 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5476. Min Act: -0.1700

Data Index: 2173424 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 3.5840. Min Range: -3.5840

Max Act: 3.5260. Min Act: -0.1690

Data Index: 447814 (Open Web Text)

Max Activating Token Index: 878