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

Dataset: Open Web Text

Neuron 820 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: 2.4782. Min Range: -2.4782

Max Act: 2.4730. Min Act: -0.0863

Data Index: 2596759 (Open Web Text)

Max Activating Token Index: 424

Text #1

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4782. Min Act: -0.1035

Data Index: 4737270 (Open Web Text)

Max Activating Token Index: 985

Text #2

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1181

Data Index: 630749 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1686

Data Index: 4777472 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1177

Data Index: 4679779 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.0863

Data Index: 4222810 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1653

Data Index: 3517338 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1493

Data Index: 3495917 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1547

Data Index: 1009018 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1327

Data Index: 3442585 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.0863

Data Index: 1503525 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.0863

Data Index: 617554 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1405

Data Index: 2363362 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4095. Min Act: -0.1109

Data Index: 421221 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1041

Data Index: 2102611 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.0863

Data Index: 348498 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.0863

Data Index: 1755759 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.0863

Data Index: 1751269 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.1064

Data Index: 1512295 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 2.4782. Min Range: -2.4782

Max Act: 2.4086. Min Act: -0.0863

Data Index: 196505 (Open Web Text)

Max Activating Token Index: 1