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

Dataset: Open Web Text

Neuron 1855 in Layer 3

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: 2.7003. Min Range: -2.7003

Max Act: 2.7003. Min Act: -0.1700

Data Index: 1090877 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6921. Min Act: -0.1700

Data Index: 5404322 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6676. Min Act: -0.1700

Data Index: 7968608 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6684. Min Act: -0.1700

Data Index: 2054865 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6517. Min Act: -0.1700

Data Index: 7332903 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6450. Min Act: -0.1700

Data Index: 4749179 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6097. Min Act: -0.1700

Data Index: 7264789 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6187. Min Act: -0.1700

Data Index: 6105632 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6000. Min Act: -0.1700

Data Index: 5213321 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5614. Min Act: -0.1700

Data Index: 7500797 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5944. Min Act: -0.1700

Data Index: 7782862 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5846. Min Act: -0.1700

Data Index: 2855640 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.6125. Min Act: -0.1700

Data Index: 5753020 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5513. Min Act: -0.1700

Data Index: 1720065 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5658. Min Act: -0.1700

Data Index: 6565629 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5773. Min Act: -0.1700

Data Index: 2855654 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5790. Min Act: -0.1700

Data Index: 2522652 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5499. Min Act: -0.1700

Data Index: 7968586 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5533. Min Act: -0.1700

Data Index: 627198 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 2.7003. Min Range: -2.7003

Max Act: 2.5625. Min Act: -0.1700

Data Index: 2560117 (Open Web Text)

Max Activating Token Index: 30