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

Dataset: Open Web Text

Neuron 2134 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: 1.4830. Min Range: -1.4830

Max Act: 1.4830. Min Act: -0.1700

Data Index: 3099108 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3963. Min Act: -0.1700

Data Index: 6108423 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3751. Min Act: -0.1700

Data Index: 5716599 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3741. Min Act: -0.1700

Data Index: 1591725 (Open Web Text)

Max Activating Token Index: 489

Text #4

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3723. Min Act: -0.1700

Data Index: 3358553 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3780. Min Act: -0.1700

Data Index: 7771726 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3827. Min Act: -0.1700

Data Index: 189005 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3686. Min Act: -0.1700

Data Index: 1723202 (Open Web Text)

Max Activating Token Index: 506

Text #8

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3650. Min Act: -0.1700

Data Index: 2071311 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3586. Min Act: -0.1700

Data Index: 2492410 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3499. Min Act: -0.1700

Data Index: 846041 (Open Web Text)

Max Activating Token Index: 454

Text #11

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3712. Min Act: -0.1700

Data Index: 667357 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3515. Min Act: -0.1700

Data Index: 5908924 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3487. Min Act: -0.1700

Data Index: 8265208 (Open Web Text)

Max Activating Token Index: 471

Text #14

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3419. Min Act: -0.1700

Data Index: 7103629 (Open Web Text)

Max Activating Token Index: 469

Text #15

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3438. Min Act: -0.1700

Data Index: 2545985 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3410. Min Act: -0.1700

Data Index: 7615929 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3484. Min Act: -0.1700

Data Index: 6467123 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3339. Min Act: -0.1700

Data Index: 8688875 (Open Web Text)

Max Activating Token Index: 547

Text #19

Max Range: 1.4830. Min Range: -1.4830

Max Act: 1.3321. Min Act: -0.1700

Data Index: 7104635 (Open Web Text)

Max Activating Token Index: 466