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

Dataset: Open Web Text

Neuron 1723 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: 3.0563. Min Range: -3.0563

Max Act: 3.0563. Min Act: -0.1700

Data Index: 2905771 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9830. Min Act: -0.1700

Data Index: 7832906 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.0563. Min Range: -3.0563

Max Act: 3.0111. Min Act: -0.1700

Data Index: 2145617 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9515. Min Act: -0.1700

Data Index: 896588 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9189. Min Act: -0.1700

Data Index: 4779417 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9054. Min Act: -0.1700

Data Index: 1278571 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7913. Min Act: -0.1700

Data Index: 2039781 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8399. Min Act: -0.1700

Data Index: 8474524 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8307. Min Act: -0.1700

Data Index: 6292742 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8602. Min Act: -0.1700

Data Index: 2865348 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.9308. Min Act: -0.1700

Data Index: 7364451 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8123. Min Act: -0.1700

Data Index: 929357 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8690. Min Act: -0.1700

Data Index: 7908669 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.8884. Min Act: -0.1700

Data Index: 3595859 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7843. Min Act: -0.1700

Data Index: 667486 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7680. Min Act: -0.1700

Data Index: 6032009 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7873. Min Act: -0.1700

Data Index: 5778324 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7714. Min Act: -0.1700

Data Index: 6964074 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7804. Min Act: -0.1700

Data Index: 4023913 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 3.0563. Min Range: -3.0563

Max Act: 2.7401. Min Act: -0.1700

Data Index: 5829701 (Open Web Text)

Max Activating Token Index: 848