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

Dataset: Open Web Text

Neuron 597 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: 0.8510. Min Range: -0.8510

Max Act: 0.8510. Min Act: -0.1700

Data Index: 724887 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7499. Min Act: -0.1700

Data Index: 320864 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7462. Min Act: -0.1700

Data Index: 6398172 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7216. Min Act: -0.1700

Data Index: 7635820 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7064. Min Act: -0.1699

Data Index: 3569638 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7109. Min Act: -0.1700

Data Index: 885247 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7010. Min Act: -0.1699

Data Index: 7730284 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6982. Min Act: -0.1700

Data Index: 2359304 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.7012. Min Act: -0.1700

Data Index: 8293021 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6977. Min Act: -0.1700

Data Index: 6779659 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6993. Min Act: -0.1699

Data Index: 1029072 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6955. Min Act: -0.1700

Data Index: 5328632 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6838. Min Act: -0.1700

Data Index: 6984972 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6841. Min Act: -0.1700

Data Index: 4652480 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6825. Min Act: -0.1700

Data Index: 3015477 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6798. Min Act: -0.1700

Data Index: 6802098 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6858. Min Act: -0.1700

Data Index: 5405392 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6838. Min Act: -0.1700

Data Index: 6540010 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6838. Min Act: -0.1700

Data Index: 5261367 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 0.8510. Min Range: -0.8510

Max Act: 0.6730. Min Act: -0.1700

Data Index: 3494076 (Open Web Text)

Max Activating Token Index: 9