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

Dataset: Open Web Text

Neuron 2594 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: 4.9867. Min Range: -4.9867

Max Act: 4.9867. Min Act: -0.1700

Data Index: 5425100 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.9724. Min Act: -0.1698

Data Index: 2202751 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.9404. Min Act: -0.1700

Data Index: 3332751 (Open Web Text)

Max Activating Token Index: 609

Text #3

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8867. Min Act: -0.1688

Data Index: 1679030 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.9051. Min Act: -0.1699

Data Index: 6083661 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8541. Min Act: -0.1695

Data Index: 7927155 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8714. Min Act: -0.1688

Data Index: 5506147 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8688. Min Act: -0.1696

Data Index: 7305493 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8831. Min Act: -0.1688

Data Index: 6211292 (Open Web Text)

Max Activating Token Index: 37

Text #9

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8354. Min Act: -0.1700

Data Index: 7531470 (Open Web Text)

Max Activating Token Index: 292

Text #10

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8372. Min Act: -0.1700

Data Index: 7378238 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8263. Min Act: -0.1688

Data Index: 7315139 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8508. Min Act: -0.1689

Data Index: 357654 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8527. Min Act: -0.1697

Data Index: 6702555 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8518. Min Act: -0.1699

Data Index: 6648999 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8588. Min Act: -0.1696

Data Index: 6089883 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8390. Min Act: -0.1688

Data Index: 654528 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8438. Min Act: -0.1688

Data Index: 653011 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8253. Min Act: -0.1699

Data Index: 6043977 (Open Web Text)

Max Activating Token Index: 288

Text #19

Max Range: 4.9867. Min Range: -4.9867

Max Act: 4.8316. Min Act: -0.1700

Data Index: 3341923 (Open Web Text)

Max Activating Token Index: 29