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

Dataset: Open Web Text

Neuron 471 in Layer 5

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: 3.6364. Min Range: -3.6364

Max Act: 3.6364. Min Act: -0.1700

Data Index: 6341401 (Open Web Text)

Max Activating Token Index: 870

Text #1

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.5436. Min Act: -0.1700

Data Index: 8210021 (Open Web Text)

Max Activating Token Index: 115

Text #2

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.5294. Min Act: -0.1700

Data Index: 326019 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.5245. Min Act: -0.1700

Data Index: 3761404 (Open Web Text)

Max Activating Token Index: 822

Text #4

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.5138. Min Act: -0.1700

Data Index: 6993167 (Open Web Text)

Max Activating Token Index: 940

Text #5

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.5190. Min Act: -0.1700

Data Index: 1317950 (Open Web Text)

Max Activating Token Index: 714

Text #6

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4984. Min Act: -0.1700

Data Index: 2939571 (Open Web Text)

Max Activating Token Index: 262

Text #7

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4764. Min Act: -0.1700

Data Index: 8168531 (Open Web Text)

Max Activating Token Index: 630

Text #8

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4746. Min Act: -0.1700

Data Index: 6319340 (Open Web Text)

Max Activating Token Index: 990

Text #9

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4877. Min Act: -0.1700

Data Index: 5511095 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4603. Min Act: -0.1700

Data Index: 7732331 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4722. Min Act: -0.1700

Data Index: 5331642 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4644. Min Act: -0.1700

Data Index: 8745687 (Open Web Text)

Max Activating Token Index: 951

Text #13

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4736. Min Act: -0.1700

Data Index: 8308902 (Open Web Text)

Max Activating Token Index: 799

Text #14

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4783. Min Act: -0.1700

Data Index: 3761411 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4591. Min Act: -0.1700

Data Index: 5054011 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4323. Min Act: -0.1700

Data Index: 977920 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4495. Min Act: -0.1700

Data Index: 3376635 (Open Web Text)

Max Activating Token Index: 408

Text #18

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4319. Min Act: -0.1700

Data Index: 4318805 (Open Web Text)

Max Activating Token Index: 462

Text #19

Max Range: 3.6364. Min Range: -3.6364

Max Act: 3.4370. Min Act: -0.1700

Data Index: 2089669 (Open Web Text)

Max Activating Token Index: 1023