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

Dataset: Open Web Text

Neuron 2813 in Layer 1

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: 3.1876. Min Range: -3.1876

Max Act: 3.1876. Min Act: -0.1700

Data Index: 8459403 (Open Web Text)

Max Activating Token Index: 432

Text #1

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.1612. Min Act: -0.1700

Data Index: 1635802 (Open Web Text)

Max Activating Token Index: 773

Text #2

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.1721. Min Act: -0.1700

Data Index: 3811584 (Open Web Text)

Max Activating Token Index: 683

Text #3

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.1531. Min Act: -0.1700

Data Index: 1451014 (Open Web Text)

Max Activating Token Index: 48

Text #4

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.1309. Min Act: -0.1700

Data Index: 2527246 (Open Web Text)

Max Activating Token Index: 797

Text #5

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0948. Min Act: -0.1700

Data Index: 8035672 (Open Web Text)

Max Activating Token Index: 543

Text #6

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.1024. Min Act: -0.1700

Data Index: 4645976 (Open Web Text)

Max Activating Token Index: 495

Text #7

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.1059. Min Act: -0.1700

Data Index: 1816031 (Open Web Text)

Max Activating Token Index: 195

Text #8

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0760. Min Act: -0.1700

Data Index: 6537396 (Open Web Text)

Max Activating Token Index: 772

Text #9

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0769. Min Act: -0.1700

Data Index: 3188011 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0872. Min Act: -0.1700

Data Index: 4262470 (Open Web Text)

Max Activating Token Index: 47

Text #11

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0666. Min Act: -0.1700

Data Index: 1076380 (Open Web Text)

Max Activating Token Index: 230

Text #12

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0461. Min Act: -0.1700

Data Index: 2910982 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0497. Min Act: -0.1700

Data Index: 3415533 (Open Web Text)

Max Activating Token Index: 452

Text #14

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0435. Min Act: -0.1700

Data Index: 8056205 (Open Web Text)

Max Activating Token Index: 180

Text #15

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0467. Min Act: -0.1700

Data Index: 4274124 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0270. Min Act: -0.1700

Data Index: 1678275 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0435. Min Act: -0.1700

Data Index: 953678 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0268. Min Act: -0.1700

Data Index: 2377447 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 3.1876. Min Range: -3.1876

Max Act: 3.0384. Min Act: -0.1700

Data Index: 953681 (Open Web Text)

Max Activating Token Index: 543