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

Dataset: Open Web Text

Neuron 1650 in Layer 0

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: 5.3127. Min Range: -5.3127

Max Act: 5.3127. Min Act: -0.1700

Data Index: 7411385 (Open Web Text)

Max Activating Token Index: 856

Text #1

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.2461. Min Act: -0.1700

Data Index: 4130796 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1900. Min Act: -0.1700

Data Index: 3811880 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1904. Min Act: -0.1700

Data Index: 809233 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.2050. Min Act: -0.1700

Data Index: 5293953 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.2032. Min Act: -0.1700

Data Index: 7905721 (Open Web Text)

Max Activating Token Index: 933

Text #6

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1697. Min Act: -0.1700

Data Index: 3735742 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1812. Min Act: -0.1700

Data Index: 5593805 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1798. Min Act: -0.1700

Data Index: 3467254 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1748. Min Act: -0.1700

Data Index: 4910581 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1606. Min Act: -0.1700

Data Index: 2078835 (Open Web Text)

Max Activating Token Index: 954

Text #11

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1743. Min Act: -0.1700

Data Index: 8773723 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1706. Min Act: -0.1700

Data Index: 2062230 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1981. Min Act: -0.1700

Data Index: 7764701 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1650. Min Act: -0.1700

Data Index: 6713043 (Open Web Text)

Max Activating Token Index: 946

Text #15

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1919. Min Act: -0.1700

Data Index: 6044203 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1617. Min Act: -0.1700

Data Index: 12916 (Open Web Text)

Max Activating Token Index: 869

Text #17

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1573. Min Act: -0.1700

Data Index: 2722222 (Open Web Text)

Max Activating Token Index: 762

Text #18

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1357. Min Act: -0.1700

Data Index: 3266672 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 5.3127. Min Range: -5.3127

Max Act: 5.1415. Min Act: -0.1700

Data Index: 5442722 (Open Web Text)

Max Activating Token Index: 882