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

Dataset: Open Web Text

Neuron 2503 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: 2.6457. Min Range: -2.6457

Max Act: 2.6457. Min Act: -0.1700

Data Index: 987785 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.6052. Min Act: -0.1700

Data Index: 8439944 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.6058. Min Act: -0.1700

Data Index: 8464729 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.6093. Min Act: -0.1700

Data Index: 4131491 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5937. Min Act: -0.1700

Data Index: 1368539 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5845. Min Act: -0.1700

Data Index: 6294504 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5777. Min Act: -0.1700

Data Index: 5165067 (Open Web Text)

Max Activating Token Index: 23

Text #7

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5878. Min Act: -0.1700

Data Index: 4596860 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5857. Min Act: -0.1700

Data Index: 8642449 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5927. Min Act: -0.1700

Data Index: 8482159 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5739. Min Act: -0.1700

Data Index: 8693083 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5772. Min Act: -0.1700

Data Index: 6133202 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5586. Min Act: -0.1700

Data Index: 6708673 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5626. Min Act: -0.1700

Data Index: 3935864 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5687. Min Act: -0.1700

Data Index: 913668 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5586. Min Act: -0.1700

Data Index: 6016855 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5590. Min Act: -0.1700

Data Index: 6315673 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5509. Min Act: -0.1700

Data Index: 6604169 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5524. Min Act: -0.1700

Data Index: 4142118 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 2.6457. Min Range: -2.6457

Max Act: 2.5512. Min Act: -0.1700

Data Index: 7514298 (Open Web Text)

Max Activating Token Index: 5