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

Dataset: Open Web Text

Neuron 1019 in Layer 4

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: 4.7034. Min Range: -4.7034

Max Act: 4.7034. Min Act: -0.1700

Data Index: 3371294 (Open Web Text)

Max Activating Token Index: 376

Text #1

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.6767. Min Act: -0.1700

Data Index: 1537430 (Open Web Text)

Max Activating Token Index: 828

Text #2

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.6081. Min Act: -0.1700

Data Index: 8649577 (Open Web Text)

Max Activating Token Index: 155

Text #3

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5368. Min Act: -0.1700

Data Index: 3862378 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.6116. Min Act: -0.1700

Data Index: 1505607 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5414. Min Act: -0.1700

Data Index: 4118039 (Open Web Text)

Max Activating Token Index: 522

Text #6

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5348. Min Act: -0.1700

Data Index: 1507934 (Open Web Text)

Max Activating Token Index: 712

Text #7

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5784. Min Act: -0.1700

Data Index: 6412502 (Open Web Text)

Max Activating Token Index: 689

Text #8

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5037. Min Act: -0.1700

Data Index: 7125196 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.4900. Min Act: -0.1700

Data Index: 5440367 (Open Web Text)

Max Activating Token Index: 251

Text #10

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5149. Min Act: -0.1700

Data Index: 6919671 (Open Web Text)

Max Activating Token Index: 420

Text #11

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.4884. Min Act: -0.1700

Data Index: 3541696 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5087. Min Act: -0.1700

Data Index: 7849911 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.4274. Min Act: -0.1700

Data Index: 5531583 (Open Web Text)

Max Activating Token Index: 607

Text #14

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5014. Min Act: -0.1700

Data Index: 1613330 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.4676. Min Act: -0.1700

Data Index: 2101941 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.5467. Min Act: -0.1700

Data Index: 5583255 (Open Web Text)

Max Activating Token Index: 845

Text #17

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.4976. Min Act: -0.1700

Data Index: 6023586 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.4971. Min Act: -0.1700

Data Index: 3090945 (Open Web Text)

Max Activating Token Index: 187

Text #19

Max Range: 4.7034. Min Range: -4.7034

Max Act: 4.4854. Min Act: -0.1700

Data Index: 6338677 (Open Web Text)

Max Activating Token Index: 223