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

Dataset: Open Web Text

Neuron 2057 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: 4.0741. Min Range: -4.0741

Max Act: 4.0733. Min Act: -0.1700

Data Index: 498918 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0741. Min Act: -0.1700

Data Index: 5425843 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0342. Min Act: -0.1700

Data Index: 126851 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0116. Min Act: -0.1700

Data Index: 1407832 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0066. Min Act: -0.1700

Data Index: 4102285 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0131. Min Act: -0.1700

Data Index: 6311206 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0172. Min Act: -0.1700

Data Index: 2069781 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0272. Min Act: -0.1700

Data Index: 8172401 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0122. Min Act: -0.1700

Data Index: 8225251 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0261. Min Act: -0.1700

Data Index: 438303 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0134. Min Act: -0.1700

Data Index: 881649 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0089. Min Act: -0.1700

Data Index: 119244 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.0741. Min Range: -4.0741

Max Act: 4.0141. Min Act: -0.1700

Data Index: 387616 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9809. Min Act: -0.1700

Data Index: 1253784 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9978. Min Act: -0.1700

Data Index: 2897378 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9873. Min Act: -0.1700

Data Index: 251489 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9886. Min Act: -0.1700

Data Index: 917508 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9853. Min Act: -0.1700

Data Index: 2810078 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9947. Min Act: -0.1700

Data Index: 212937 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.0741. Min Range: -4.0741

Max Act: 3.9706. Min Act: -0.1700

Data Index: 2478999 (Open Web Text)

Max Activating Token Index: 7