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

Dataset: Open Web Text

Neuron 2223 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: 4.0643. Min Range: -4.0643

Max Act: 4.0643. Min Act: -0.1700

Data Index: 8483537 (Open Web Text)

Max Activating Token Index: 690

Text #1

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0246. Min Act: -0.1700

Data Index: 953192 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0415. Min Act: -0.1700

Data Index: 7938352 (Open Web Text)

Max Activating Token Index: 885

Text #3

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0181. Min Act: -0.1700

Data Index: 4285591 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9809. Min Act: -0.1700

Data Index: 2057330 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0032. Min Act: -0.1700

Data Index: 1641210 (Open Web Text)

Max Activating Token Index: 94

Text #6

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9810. Min Act: -0.1700

Data Index: 7708930 (Open Web Text)

Max Activating Token Index: 853

Text #7

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9827. Min Act: -0.1700

Data Index: 1469233 (Open Web Text)

Max Activating Token Index: 835

Text #8

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9733. Min Act: -0.1700

Data Index: 4797407 (Open Web Text)

Max Activating Token Index: 628

Text #9

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9666. Min Act: -0.1700

Data Index: 7156934 (Open Web Text)

Max Activating Token Index: 753

Text #10

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9455. Min Act: -0.1700

Data Index: 7005472 (Open Web Text)

Max Activating Token Index: 821

Text #11

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9493. Min Act: -0.1700

Data Index: 1028970 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9618. Min Act: -0.1700

Data Index: 3444410 (Open Web Text)

Max Activating Token Index: 311

Text #13

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9619. Min Act: -0.1700

Data Index: 1365811 (Open Web Text)

Max Activating Token Index: 740

Text #14

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9390. Min Act: -0.1700

Data Index: 5418699 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9206. Min Act: -0.1700

Data Index: 1572832 (Open Web Text)

Max Activating Token Index: 503

Text #16

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9058. Min Act: -0.1700

Data Index: 6027352 (Open Web Text)

Max Activating Token Index: 394

Text #17

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9259. Min Act: -0.1700

Data Index: 1087681 (Open Web Text)

Max Activating Token Index: 157

Text #18

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9469. Min Act: -0.1700

Data Index: 1737626 (Open Web Text)

Max Activating Token Index: 940

Text #19

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.8985. Min Act: -0.1700

Data Index: 6601819 (Open Web Text)

Max Activating Token Index: 531