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

Dataset: Open Web Text

Neuron 1565 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: 2.6544. Min Range: -2.6544

Max Act: 2.6544. Min Act: -0.1700

Data Index: 1108911 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6269. Min Act: -0.1700

Data Index: 8671413 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6263. Min Act: -0.1700

Data Index: 7137442 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6183. Min Act: -0.1700

Data Index: 7111739 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6081. Min Act: -0.1700

Data Index: 6844058 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6212. Min Act: -0.1700

Data Index: 2936397 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6125. Min Act: -0.1700

Data Index: 1591063 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6081. Min Act: -0.1700

Data Index: 5768961 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6051. Min Act: -0.1700

Data Index: 858180 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.6012. Min Act: -0.1700

Data Index: 4474786 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5878. Min Act: -0.1700

Data Index: 3515399 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5898. Min Act: -0.1700

Data Index: 2347605 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5906. Min Act: -0.1700

Data Index: 3738743 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5878. Min Act: -0.1700

Data Index: 6035839 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5749. Min Act: -0.1700

Data Index: 2867450 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5910. Min Act: -0.1700

Data Index: 939529 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5824. Min Act: -0.1700

Data Index: 2086320 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5884. Min Act: -0.1700

Data Index: 5637010 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5878. Min Act: -0.1700

Data Index: 5401884 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.6544. Min Range: -2.6544

Max Act: 2.5878. Min Act: -0.1700

Data Index: 1746196 (Open Web Text)

Max Activating Token Index: 2