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

Dataset: Open Web Text

Neuron 614 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: 4.1134. Min Range: -4.1134

Max Act: 4.1134. Min Act: -0.1698

Data Index: 2646215 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.1134. Min Range: -4.1134

Max Act: 4.0740. Min Act: -0.1697

Data Index: 8375988 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.9589. Min Act: -0.1698

Data Index: 1147604 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.9390. Min Act: -0.1699

Data Index: 1692644 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.9242. Min Act: -0.1696

Data Index: 17482 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8905. Min Act: -0.1700

Data Index: 6753158 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.9651. Min Act: -0.1694

Data Index: 3800057 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8764. Min Act: -0.1698

Data Index: 7489686 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.9062. Min Act: -0.1700

Data Index: 8482452 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8736. Min Act: -0.1700

Data Index: 8091385 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8929. Min Act: -0.1686

Data Index: 5607599 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8546. Min Act: -0.1676

Data Index: 2413811 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8790. Min Act: -0.1700

Data Index: 1635686 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8792. Min Act: -0.1699

Data Index: 7682758 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8222. Min Act: -0.1700

Data Index: 3189108 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8105. Min Act: -0.1696

Data Index: 8142050 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8433. Min Act: -0.1689

Data Index: 1615787 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8154. Min Act: -0.1698

Data Index: 1141696 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8350. Min Act: -0.1700

Data Index: 2951965 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.7782. Min Act: -0.1684

Data Index: 520215 (Open Web Text)

Max Activating Token Index: 1023