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

Dataset: Open Web Text

Neuron 2576 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: 4.2659. Min Range: -4.2659

Max Act: 4.2659. Min Act: -0.1700

Data Index: 8004765 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.1830. Min Act: -0.1700

Data Index: 2297513 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.1376. Min Act: -0.1700

Data Index: 1331554 (Open Web Text)

Max Activating Token Index: 472

Text #3

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.1251. Min Act: -0.1700

Data Index: 3640230 (Open Web Text)

Max Activating Token Index: 906

Text #4

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.1183. Min Act: -0.1700

Data Index: 2537574 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.1007. Min Act: -0.1700

Data Index: 4072351 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0721. Min Act: -0.1700

Data Index: 2537573 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0608. Min Act: -0.1700

Data Index: 8580744 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0696. Min Act: -0.1700

Data Index: 2706612 (Open Web Text)

Max Activating Token Index: 391

Text #9

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0405. Min Act: -0.1700

Data Index: 4110798 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0454. Min Act: -0.1700

Data Index: 5101839 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0491. Min Act: -0.1700

Data Index: 2406675 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0576. Min Act: -0.1700

Data Index: 19541 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0318. Min Act: -0.1700

Data Index: 3975984 (Open Web Text)

Max Activating Token Index: 311

Text #14

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0355. Min Act: -0.1700

Data Index: 6560329 (Open Web Text)

Max Activating Token Index: 43

Text #15

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0089. Min Act: -0.1700

Data Index: 908617 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 4.2659. Min Range: -4.2659

Max Act: 4.0352. Min Act: -0.1700

Data Index: 775504 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 4.2659. Min Range: -4.2659

Max Act: 3.9982. Min Act: -0.1700

Data Index: 1574850 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 4.2659. Min Range: -4.2659

Max Act: 3.9925. Min Act: -0.1700

Data Index: 4340336 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 4.2659. Min Range: -4.2659

Max Act: 3.9692. Min Act: -0.1700

Data Index: 3385798 (Open Web Text)

Max Activating Token Index: 46