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

Dataset: Open Web Text

Neuron 2075 in Layer 5

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: 3.0971. Min Range: -3.0971

Max Act: 3.0971. Min Act: -0.1700

Data Index: 3547662 (Open Web Text)

Max Activating Token Index: 728

Text #1

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0811. Min Act: -0.1700

Data Index: 1794612 (Open Web Text)

Max Activating Token Index: 574

Text #2

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0813. Min Act: -0.1700

Data Index: 1512295 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0528. Min Act: -0.1700

Data Index: 1842884 (Open Web Text)

Max Activating Token Index: 46

Text #4

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0601. Min Act: -0.1700

Data Index: 6097426 (Open Web Text)

Max Activating Token Index: 809

Text #5

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0454. Min Act: -0.1700

Data Index: 8758908 (Open Web Text)

Max Activating Token Index: 283

Text #6

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0382. Min Act: -0.1700

Data Index: 7739919 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0332. Min Act: -0.1700

Data Index: 7431462 (Open Web Text)

Max Activating Token Index: 490

Text #8

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0635. Min Act: -0.1700

Data Index: 2182311 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1417734 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0291. Min Act: -0.1700

Data Index: 3153608 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0061. Min Act: -0.1700

Data Index: 5730106 (Open Web Text)

Max Activating Token Index: 125

Text #12

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0039. Min Act: -0.1700

Data Index: 5836285 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0261. Min Act: -0.1700

Data Index: 4817660 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 3.0971. Min Range: -3.0971

Max Act: 2.9801. Min Act: -0.1700

Data Index: 1586912 (Open Web Text)

Max Activating Token Index: 991

Text #15

Max Range: 3.0971. Min Range: -3.0971

Max Act: 2.9722. Min Act: -0.1700

Data Index: 3161071 (Open Web Text)

Max Activating Token Index: 312

Text #16

Max Range: 3.0971. Min Range: -3.0971

Max Act: 2.9911. Min Act: -0.1700

Data Index: 1165872 (Open Web Text)

Max Activating Token Index: 325

Text #17

Max Range: 3.0971. Min Range: -3.0971

Max Act: 2.9827. Min Act: -0.1700

Data Index: 5321028 (Open Web Text)

Max Activating Token Index: 748

Text #18

Max Range: 3.0971. Min Range: -3.0971

Max Act: 2.9908. Min Act: -0.1700

Data Index: 5693328 (Open Web Text)

Max Activating Token Index: 338

Text #19

Max Range: 3.0971. Min Range: -3.0971

Max Act: 3.0012. Min Act: -0.1700

Data Index: 1413582 (Open Web Text)

Max Activating Token Index: 540