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

Dataset: Open Web Text

Neuron 10 in Layer 3

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: 3.1461. Min Range: -3.1461

Max Act: 3.1461. Min Act: -0.1700

Data Index: 7755060 (Open Web Text)

Max Activating Token Index: 996

Text #1

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0803. Min Act: -0.1700

Data Index: 2008723 (Open Web Text)

Max Activating Token Index: 933

Text #2

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0758. Min Act: -0.1700

Data Index: 462092 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0795. Min Act: -0.1700

Data Index: 7724793 (Open Web Text)

Max Activating Token Index: 707

Text #4

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0850. Min Act: -0.1700

Data Index: 4725360 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0866. Min Act: -0.1700

Data Index: 4293889 (Open Web Text)

Max Activating Token Index: 859

Text #6

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0779. Min Act: -0.1700

Data Index: 5509596 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0670. Min Act: -0.1700

Data Index: 7516271 (Open Web Text)

Max Activating Token Index: 866

Text #8

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0508. Min Act: -0.1700

Data Index: 5802314 (Open Web Text)

Max Activating Token Index: 867

Text #9

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0422. Min Act: -0.1700

Data Index: 6368290 (Open Web Text)

Max Activating Token Index: 917

Text #10

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0538. Min Act: -0.1700

Data Index: 4744439 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0386. Min Act: -0.1700

Data Index: 7755400 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0618. Min Act: -0.1700

Data Index: 5371116 (Open Web Text)

Max Activating Token Index: 784

Text #13

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0580. Min Act: -0.1700

Data Index: 1806622 (Open Web Text)

Max Activating Token Index: 792

Text #14

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0502. Min Act: -0.1700

Data Index: 5382530 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0453. Min Act: -0.1700

Data Index: 3858151 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0597. Min Act: -0.1700

Data Index: 7745513 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0518. Min Act: -0.1700

Data Index: 1940222 (Open Web Text)

Max Activating Token Index: 1003

Text #18

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0410. Min Act: -0.1700

Data Index: 6441393 (Open Web Text)

Max Activating Token Index: 511

Text #19

Max Range: 3.1461. Min Range: -3.1461

Max Act: 3.0520. Min Act: -0.1700

Data Index: 7062030 (Open Web Text)

Max Activating Token Index: 743