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

Dataset: Open Web Text

Neuron 1030 in Layer 6

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: 4.6825. Min Range: -4.6825

Max Act: 4.6825. Min Act: -0.1700

Data Index: 308666 (Open Web Text)

Max Activating Token Index: 790

Text #1

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.6133. Min Act: -0.1700

Data Index: 3771978 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.5685. Min Act: -0.1700

Data Index: 5483328 (Open Web Text)

Max Activating Token Index: 903

Text #3

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.5307. Min Act: -0.1700

Data Index: 7938517 (Open Web Text)

Max Activating Token Index: 724

Text #4

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.5001. Min Act: -0.1700

Data Index: 3569211 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.4927. Min Act: -0.1700

Data Index: 496181 (Open Web Text)

Max Activating Token Index: 604

Text #6

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.4936. Min Act: -0.1700

Data Index: 180020 (Open Web Text)

Max Activating Token Index: 796

Text #7

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.4307. Min Act: -0.1700

Data Index: 1189098 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.4186. Min Act: -0.1700

Data Index: 3601595 (Open Web Text)

Max Activating Token Index: 836

Text #9

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3856. Min Act: -0.1700

Data Index: 4361691 (Open Web Text)

Max Activating Token Index: 972

Text #10

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.4091. Min Act: -0.1700

Data Index: 1452385 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3924. Min Act: -0.1700

Data Index: 7819265 (Open Web Text)

Max Activating Token Index: 495

Text #12

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3996. Min Act: -0.1700

Data Index: 2782988 (Open Web Text)

Max Activating Token Index: 872

Text #13

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3753. Min Act: -0.1700

Data Index: 440714 (Open Web Text)

Max Activating Token Index: 666

Text #14

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3863. Min Act: -0.1700

Data Index: 6973436 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3907. Min Act: -0.1700

Data Index: 6860779 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3683. Min Act: -0.1700

Data Index: 1966520 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3778. Min Act: -0.1700

Data Index: 842275 (Open Web Text)

Max Activating Token Index: 326

Text #18

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3489. Min Act: -0.1700

Data Index: 3129857 (Open Web Text)

Max Activating Token Index: 761

Text #19

Max Range: 4.6825. Min Range: -4.6825

Max Act: 4.3730. Min Act: -0.1700

Data Index: 5675341 (Open Web Text)

Max Activating Token Index: 285