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

Dataset: Open Web Text

Neuron 78 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: 4.2782. Min Range: -4.2782

Max Act: 4.2782. Min Act: -0.1700

Data Index: 6328226 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2646. Min Act: -0.1700

Data Index: 8144090 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2105. Min Act: -0.1700

Data Index: 2138133 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.2008. Min Act: -0.1700

Data Index: 5979173 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1675. Min Act: -0.1700

Data Index: 1025047 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1802. Min Act: -0.1700

Data Index: 190321 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1704. Min Act: -0.1700

Data Index: 131386 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1802. Min Act: -0.1700

Data Index: 107818 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1791. Min Act: -0.1700

Data Index: 3684963 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1389. Min Act: -0.1700

Data Index: 2997906 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1293. Min Act: -0.1700

Data Index: 7307257 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1333. Min Act: -0.1700

Data Index: 8040372 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1390. Min Act: -0.1700

Data Index: 8655989 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.1182. Min Act: -0.1700

Data Index: 5927844 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.0832. Min Act: -0.1700

Data Index: 4181419 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.0810. Min Act: -0.1700

Data Index: 1591674 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.0687. Min Act: -0.1700

Data Index: 494491 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.0631. Min Act: -0.1700

Data Index: 1664550 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.0738. Min Act: -0.1700

Data Index: 3299029 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.2782. Min Range: -4.2782

Max Act: 4.0535. Min Act: -0.1700

Data Index: 3753465 (Open Web Text)

Max Activating Token Index: 843