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

Dataset: Open Web Text

Neuron 2678 in Layer 2

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: 1.2904. Min Range: -1.2904

Max Act: 1.2904. Min Act: -0.1700

Data Index: 4543222 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.2492. Min Act: -0.1699

Data Index: 331553 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.2051. Min Act: -0.1700

Data Index: 1609535 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1536. Min Act: -0.1700

Data Index: 3647705 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1128. Min Act: -0.1700

Data Index: 330187 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.1282. Min Act: -0.1700

Data Index: 5304010 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0975. Min Act: -0.1700

Data Index: 1640348 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0888. Min Act: -0.1700

Data Index: 4157623 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0744. Min Act: -0.1700

Data Index: 2097964 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0892. Min Act: -0.1700

Data Index: 8238753 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0759. Min Act: -0.1700

Data Index: 314694 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0813. Min Act: -0.1700

Data Index: 500419 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0804. Min Act: -0.1700

Data Index: 2251064 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0777. Min Act: -0.1700

Data Index: 1471127 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0927. Min Act: -0.1700

Data Index: 3138781 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0666. Min Act: -0.1700

Data Index: 555753 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0675. Min Act: -0.1700

Data Index: 1890804 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0640. Min Act: -0.1700

Data Index: 8255442 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0659. Min Act: -0.1700

Data Index: 4429406 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.2904. Min Range: -1.2904

Max Act: 1.0649. Min Act: -0.1700

Data Index: 8196298 (Open Web Text)

Max Activating Token Index: 1023