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

Dataset: Open Web Text

Neuron 860 in Layer 3

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: 3.7325. Min Range: -3.7325

Max Act: 3.7109. Min Act: -0.1700

Data Index: 5837245 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.7305. Min Act: -0.1700

Data Index: 2794871 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.7325. Min Act: -0.1700

Data Index: 4635865 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.7128. Min Act: -0.1700

Data Index: 6692891 (Open Web Text)

Max Activating Token Index: 463

Text #4

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6458. Min Act: -0.1700

Data Index: 8080138 (Open Web Text)

Max Activating Token Index: 798

Text #5

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.7265. Min Act: -0.1700

Data Index: 5735932 (Open Web Text)

Max Activating Token Index: 532

Text #6

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6905. Min Act: -0.1700

Data Index: 4794317 (Open Web Text)

Max Activating Token Index: 682

Text #7

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6659. Min Act: -0.1700

Data Index: 750113 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6859. Min Act: -0.1700

Data Index: 341860 (Open Web Text)

Max Activating Token Index: 532

Text #9

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6614. Min Act: -0.1700

Data Index: 3606482 (Open Web Text)

Max Activating Token Index: 746

Text #10

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6591. Min Act: -0.1700

Data Index: 613570 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6689. Min Act: -0.1700

Data Index: 1914780 (Open Web Text)

Max Activating Token Index: 278

Text #12

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6634. Min Act: -0.1700

Data Index: 860709 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6595. Min Act: -0.1700

Data Index: 4343610 (Open Web Text)

Max Activating Token Index: 1001

Text #14

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6640. Min Act: -0.1700

Data Index: 4518067 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6283. Min Act: -0.1700

Data Index: 3442376 (Open Web Text)

Max Activating Token Index: 821

Text #16

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6183. Min Act: -0.1700

Data Index: 3100230 (Open Web Text)

Max Activating Token Index: 935

Text #17

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6568. Min Act: -0.1700

Data Index: 2208129 (Open Web Text)

Max Activating Token Index: 732

Text #18

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6665. Min Act: -0.1700

Data Index: 1891020 (Open Web Text)

Max Activating Token Index: 590

Text #19

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6047. Min Act: -0.1700

Data Index: 860311 (Open Web Text)

Max Activating Token Index: 568