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

Dataset: Open Web Text

Neuron 2315 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: 1.9398. Min Range: -1.9398

Max Act: 1.9398. Min Act: -0.1700

Data Index: 6213935 (Open Web Text)

Max Activating Token Index: 670

Text #1

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8964. Min Act: -0.1700

Data Index: 480480 (Open Web Text)

Max Activating Token Index: 557

Text #2

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.9098. Min Act: -0.1700

Data Index: 7974270 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.9057. Min Act: -0.1700

Data Index: 8697828 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8952. Min Act: -0.1700

Data Index: 6672545 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8634. Min Act: -0.1700

Data Index: 6022428 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8724. Min Act: -0.1700

Data Index: 4381849 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8890. Min Act: -0.1700

Data Index: 624058 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8847. Min Act: -0.1699

Data Index: 7032630 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8707. Min Act: -0.1700

Data Index: 6527602 (Open Web Text)

Max Activating Token Index: 94

Text #10

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8721. Min Act: -0.1700

Data Index: 6088559 (Open Web Text)

Max Activating Token Index: 245

Text #11

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8665. Min Act: -0.1700

Data Index: 576538 (Open Web Text)

Max Activating Token Index: 99

Text #12

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8517. Min Act: -0.1700

Data Index: 8086116 (Open Web Text)

Max Activating Token Index: 767

Text #13

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8495. Min Act: -0.1700

Data Index: 1874738 (Open Web Text)

Max Activating Token Index: 157

Text #14

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8313. Min Act: -0.1700

Data Index: 8209412 (Open Web Text)

Max Activating Token Index: 640

Text #15

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8389. Min Act: -0.1699

Data Index: 4249933 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8226. Min Act: -0.1700

Data Index: 7076857 (Open Web Text)

Max Activating Token Index: 779

Text #17

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8334. Min Act: -0.1700

Data Index: 2768530 (Open Web Text)

Max Activating Token Index: 93

Text #18

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8299. Min Act: -0.1700

Data Index: 1838556 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 1.9398. Min Range: -1.9398

Max Act: 1.8383. Min Act: -0.1699

Data Index: 8092220 (Open Web Text)

Max Activating Token Index: 618