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

Dataset: Open Web Text

Neuron 2398 in Layer 6

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: 3.8303. Min Range: -3.8303

Max Act: 3.7862. Min Act: -0.1700

Data Index: 1144196 (Open Web Text)

Max Activating Token Index: 742

Text #1

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.8303. Min Act: -0.1700

Data Index: 1460980 (Open Web Text)

Max Activating Token Index: 934

Text #2

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7656. Min Act: -0.1700

Data Index: 5743078 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.7111. Min Act: -0.1700

Data Index: 5740404 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6618. Min Act: -0.1700

Data Index: 5791835 (Open Web Text)

Max Activating Token Index: 366

Text #5

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6136. Min Act: -0.1700

Data Index: 5620687 (Open Web Text)

Max Activating Token Index: 906

Text #6

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6306. Min Act: -0.1700

Data Index: 4754890 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6287. Min Act: -0.1700

Data Index: 8680961 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.6162. Min Act: -0.1700

Data Index: 2938582 (Open Web Text)

Max Activating Token Index: 503

Text #9

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5722. Min Act: -0.1700

Data Index: 430318 (Open Web Text)

Max Activating Token Index: 434

Text #10

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5701. Min Act: -0.1700

Data Index: 8303801 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5643. Min Act: -0.1700

Data Index: 3245943 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5656. Min Act: -0.1700

Data Index: 6148143 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5516. Min Act: -0.1700

Data Index: 5031779 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5753. Min Act: -0.1700

Data Index: 6958588 (Open Web Text)

Max Activating Token Index: 609

Text #15

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5405. Min Act: -0.1700

Data Index: 8049598 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5581. Min Act: -0.1700

Data Index: 4494171 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5525. Min Act: -0.1700

Data Index: 1891120 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5713. Min Act: -0.1700

Data Index: 1845945 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 3.8303. Min Range: -3.8303

Max Act: 3.5476. Min Act: -0.1700

Data Index: 261889 (Open Web Text)

Max Activating Token Index: 315