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

Dataset: Open Web Text

Neuron 2715 in Layer 0

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: 3.1422. Min Range: -3.1422

Max Act: 3.1422. Min Act: -0.1700

Data Index: 2844032 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.1358. Min Act: -0.1700

Data Index: 5783594 (Open Web Text)

Max Activating Token Index: 950

Text #2

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.1268. Min Act: -0.1700

Data Index: 1761403 (Open Web Text)

Max Activating Token Index: 1004

Text #3

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.1067. Min Act: -0.1700

Data Index: 3153546 (Open Web Text)

Max Activating Token Index: 116

Text #4

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.1018. Min Act: -0.1700

Data Index: 2016998 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0903. Min Act: -0.1700

Data Index: 6640942 (Open Web Text)

Max Activating Token Index: 736

Text #6

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0880. Min Act: -0.1700

Data Index: 6827198 (Open Web Text)

Max Activating Token Index: 721

Text #7

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0891. Min Act: -0.1700

Data Index: 1574340 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0803. Min Act: -0.1700

Data Index: 7887934 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0987. Min Act: -0.1700

Data Index: 4971476 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0682. Min Act: -0.1700

Data Index: 148698 (Open Web Text)

Max Activating Token Index: 156

Text #11

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0664. Min Act: -0.1700

Data Index: 1929644 (Open Web Text)

Max Activating Token Index: 261

Text #12

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0568. Min Act: -0.1700

Data Index: 4210304 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0529. Min Act: -0.1700

Data Index: 7669448 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0602. Min Act: -0.1700

Data Index: 7365545 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0548. Min Act: -0.1700

Data Index: 2347430 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0581. Min Act: -0.1700

Data Index: 7040219 (Open Web Text)

Max Activating Token Index: 708

Text #17

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0637. Min Act: -0.1700

Data Index: 8332057 (Open Web Text)

Max Activating Token Index: 843

Text #18

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0516. Min Act: -0.1700

Data Index: 3050543 (Open Web Text)

Max Activating Token Index: 672

Text #19

Max Range: 3.1422. Min Range: -3.1422

Max Act: 3.0551. Min Act: -0.1700

Data Index: 6456455 (Open Web Text)

Max Activating Token Index: 95