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

Dataset: Open Web Text

Neuron 2183 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: 4.2610. Min Range: -4.2610

Max Act: 4.2610. Min Act: -0.1700

Data Index: 5772711 (Open Web Text)

Max Activating Token Index: 506

Text #1

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.2163. Min Act: -0.1700

Data Index: 5984260 (Open Web Text)

Max Activating Token Index: 867

Text #2

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.1558. Min Act: -0.1700

Data Index: 2848979 (Open Web Text)

Max Activating Token Index: 148

Text #3

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.1408. Min Act: -0.1700

Data Index: 6544672 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.1255. Min Act: -0.1700

Data Index: 6979413 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.1551. Min Act: -0.1700

Data Index: 1980340 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.1193. Min Act: -0.1700

Data Index: 8753469 (Open Web Text)

Max Activating Token Index: 383

Text #7

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.1169. Min Act: -0.1700

Data Index: 5540800 (Open Web Text)

Max Activating Token Index: 710

Text #8

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.1007. Min Act: -0.1700

Data Index: 1383678 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0757. Min Act: -0.1700

Data Index: 4418524 (Open Web Text)

Max Activating Token Index: 664

Text #10

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0910. Min Act: -0.1700

Data Index: 3579566 (Open Web Text)

Max Activating Token Index: 943

Text #11

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0834. Min Act: -0.1700

Data Index: 8421750 (Open Web Text)

Max Activating Token Index: 496

Text #12

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0830. Min Act: -0.1700

Data Index: 2462675 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0664. Min Act: -0.1700

Data Index: 6886008 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0759. Min Act: -0.1700

Data Index: 7092554 (Open Web Text)

Max Activating Token Index: 96

Text #15

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0822. Min Act: -0.1700

Data Index: 4889460 (Open Web Text)

Max Activating Token Index: 165

Text #16

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0707. Min Act: -0.1700

Data Index: 5600620 (Open Web Text)

Max Activating Token Index: 882

Text #17

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0675. Min Act: -0.1700

Data Index: 6886006 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0475. Min Act: -0.1700

Data Index: 3025634 (Open Web Text)

Max Activating Token Index: 647

Text #19

Max Range: 4.2610. Min Range: -4.2610

Max Act: 4.0581. Min Act: -0.1700

Data Index: 734778 (Open Web Text)

Max Activating Token Index: 423