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

Dataset: Open Web Text

Neuron 1963 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: 3.3322. Min Range: -3.3322

Max Act: 3.3322. Min Act: -0.1700

Data Index: 1725705 (Open Web Text)

Max Activating Token Index: 871

Text #1

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2753. Min Act: -0.1700

Data Index: 5463216 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2949. Min Act: -0.1700

Data Index: 3694807 (Open Web Text)

Max Activating Token Index: 812

Text #3

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2488. Min Act: -0.1700

Data Index: 5697746 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2935. Min Act: -0.1700

Data Index: 8490641 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2582. Min Act: -0.1700

Data Index: 7054517 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2173. Min Act: -0.1700

Data Index: 4526445 (Open Web Text)

Max Activating Token Index: 862

Text #7

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2013. Min Act: -0.1700

Data Index: 2239124 (Open Web Text)

Max Activating Token Index: 656

Text #8

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1932. Min Act: -0.1700

Data Index: 5272820 (Open Web Text)

Max Activating Token Index: 463

Text #9

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.2072. Min Act: -0.1700

Data Index: 4117509 (Open Web Text)

Max Activating Token Index: 1017

Text #10

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1572. Min Act: -0.1700

Data Index: 2657520 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1668. Min Act: -0.1700

Data Index: 1455341 (Open Web Text)

Max Activating Token Index: 892

Text #12

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1590. Min Act: -0.1700

Data Index: 4947838 (Open Web Text)

Max Activating Token Index: 337

Text #13

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1618. Min Act: -0.1700

Data Index: 3118843 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1415. Min Act: -0.1700

Data Index: 6075322 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1493. Min Act: -0.1700

Data Index: 4302976 (Open Web Text)

Max Activating Token Index: 202

Text #16

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1575. Min Act: -0.1700

Data Index: 8683205 (Open Web Text)

Max Activating Token Index: 970

Text #17

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1265. Min Act: -0.1700

Data Index: 7528882 (Open Web Text)

Max Activating Token Index: 1000

Text #18

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.0941. Min Act: -0.1700

Data Index: 1712429 (Open Web Text)

Max Activating Token Index: 847

Text #19

Max Range: 3.3322. Min Range: -3.3322

Max Act: 3.1367. Min Act: -0.1700

Data Index: 6321752 (Open Web Text)

Max Activating Token Index: 544