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

Dataset: Open Web Text

Neuron 2478 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: 3.2057. Min Range: -3.2057

Max Act: 3.2057. Min Act: -0.1700

Data Index: 7451262 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.0681. Min Act: -0.1700

Data Index: 6189809 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.0449. Min Act: -0.1700

Data Index: 238513 (Open Web Text)

Max Activating Token Index: 25

Text #3

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.0444. Min Act: -0.1700

Data Index: 1893882 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.0495. Min Act: -0.1700

Data Index: 7875574 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.0085. Min Act: -0.1700

Data Index: 4825660 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.0130. Min Act: -0.1700

Data Index: 6440887 (Open Web Text)

Max Activating Token Index: 66

Text #7

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9996. Min Act: -0.1700

Data Index: 992735 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9875. Min Act: -0.1700

Data Index: 3286831 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9982. Min Act: -0.1700

Data Index: 5499573 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9888. Min Act: -0.1700

Data Index: 1178823 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9945. Min Act: -0.1700

Data Index: 3823257 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.2057. Min Range: -3.2057

Max Act: 3.0030. Min Act: -0.1700

Data Index: 1560863 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9903. Min Act: -0.1700

Data Index: 7994815 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9786. Min Act: -0.1700

Data Index: 8100181 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9623. Min Act: -0.1700

Data Index: 2946970 (Open Web Text)

Max Activating Token Index: 569

Text #16

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9831. Min Act: -0.1700

Data Index: 1159430 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9829. Min Act: -0.1700

Data Index: 1848090 (Open Web Text)

Max Activating Token Index: 829

Text #18

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9860. Min Act: -0.1700

Data Index: 5058399 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.2057. Min Range: -3.2057

Max Act: 2.9776. Min Act: -0.1700

Data Index: 571218 (Open Web Text)

Max Activating Token Index: 72