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

Dataset: Open Web Text

Neuron 582 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: 5.1825. Min Range: -5.1825

Max Act: 5.1825. Min Act: -0.1700

Data Index: 6379175 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.1307. Min Act: -0.1700

Data Index: 8054266 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0665. Min Act: -0.1700

Data Index: 3536355 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0955. Min Act: -0.1700

Data Index: 3765303 (Open Web Text)

Max Activating Token Index: 966

Text #4

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0518. Min Act: -0.1700

Data Index: 293048 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0480. Min Act: -0.1700

Data Index: 2975492 (Open Web Text)

Max Activating Token Index: 903

Text #6

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0640. Min Act: -0.1700

Data Index: 132874 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0279. Min Act: -0.1700

Data Index: 8594630 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0214. Min Act: -0.1700

Data Index: 4528775 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0201. Min Act: -0.1700

Data Index: 577942 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0052. Min Act: -0.1700

Data Index: 1368773 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0111. Min Act: -0.1700

Data Index: 128045 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9831. Min Act: -0.1700

Data Index: 2742269 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0060. Min Act: -0.1700

Data Index: 7362601 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9986. Min Act: -0.1700

Data Index: 3352476 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.1825. Min Range: -5.1825

Max Act: 5.0036. Min Act: -0.1700

Data Index: 3241386 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9486. Min Act: -0.1700

Data Index: 4190021 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9655. Min Act: -0.1700

Data Index: 1326535 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9561. Min Act: -0.1700

Data Index: 233404 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 5.1825. Min Range: -5.1825

Max Act: 4.9493. Min Act: -0.1700

Data Index: 611813 (Open Web Text)

Max Activating Token Index: 3