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

Dataset: Open Web Text

Neuron 2637 in Layer 1

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: 1.4317. Min Range: -1.4317

Max Act: 1.4317. Min Act: -0.1700

Data Index: 3438511 (Open Web Text)

Max Activating Token Index: 655

Text #1

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.4276. Min Act: -0.1698

Data Index: 1107499 (Open Web Text)

Max Activating Token Index: 150

Text #2

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.4082. Min Act: -0.1700

Data Index: 8577753 (Open Web Text)

Max Activating Token Index: 417

Text #3

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.4054. Min Act: -0.1662

Data Index: 850700 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3878. Min Act: -0.1696

Data Index: 1737641 (Open Web Text)

Max Activating Token Index: 668

Text #5

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3850. Min Act: -0.1700

Data Index: 2669764 (Open Web Text)

Max Activating Token Index: 325

Text #6

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3867. Min Act: -0.1700

Data Index: 4057387 (Open Web Text)

Max Activating Token Index: 778

Text #7

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3694. Min Act: -0.1700

Data Index: 1054724 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3769. Min Act: -0.1700

Data Index: 106482 (Open Web Text)

Max Activating Token Index: 407

Text #9

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3876. Min Act: -0.1682

Data Index: 6612726 (Open Web Text)

Max Activating Token Index: 912

Text #10

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3689. Min Act: -0.1700

Data Index: 3207561 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3644. Min Act: -0.1700

Data Index: 7321443 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3607. Min Act: -0.1689

Data Index: 2930665 (Open Web Text)

Max Activating Token Index: 275

Text #13

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3528. Min Act: -0.1700

Data Index: 496551 (Open Web Text)

Max Activating Token Index: 691

Text #14

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3601. Min Act: -0.1688

Data Index: 5924806 (Open Web Text)

Max Activating Token Index: 918

Text #15

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3616. Min Act: -0.1700

Data Index: 1995716 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3564. Min Act: -0.1700

Data Index: 5460113 (Open Web Text)

Max Activating Token Index: 109

Text #17

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3432. Min Act: -0.1696

Data Index: 7136492 (Open Web Text)

Max Activating Token Index: 475

Text #18

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3376. Min Act: -0.1699

Data Index: 2734504 (Open Web Text)

Max Activating Token Index: 808

Text #19

Max Range: 1.4317. Min Range: -1.4317

Max Act: 1.3421. Min Act: -0.1700

Data Index: 925308 (Open Web Text)

Max Activating Token Index: 390