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

Dataset: Open Web Text

Neuron 1323 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: 2.9736. Min Range: -2.9736

Max Act: 2.9736. Min Act: -0.1700

Data Index: 5069234 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9618. Min Act: -0.1700

Data Index: 6149580 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9681. Min Act: -0.1700

Data Index: 1353058 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9416. Min Act: -0.1700

Data Index: 2210831 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9427. Min Act: -0.1700

Data Index: 6594245 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9049. Min Act: -0.1700

Data Index: 7724241 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9102. Min Act: -0.1700

Data Index: 4553605 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.9068. Min Act: -0.1700

Data Index: 7943347 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8838. Min Act: -0.1700

Data Index: 1375170 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8653. Min Act: -0.1700

Data Index: 5351549 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8535. Min Act: -0.1700

Data Index: 8000715 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8534. Min Act: -0.1700

Data Index: 316668 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8626. Min Act: -0.1700

Data Index: 1317873 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8569. Min Act: -0.1700

Data Index: 1117527 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8658. Min Act: -0.1700

Data Index: 2569643 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8430. Min Act: -0.1700

Data Index: 3484106 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8356. Min Act: -0.1700

Data Index: 6841633 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8356. Min Act: -0.1700

Data Index: 4085650 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8262. Min Act: -0.1700

Data Index: 6714094 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.9736. Min Range: -2.9736

Max Act: 2.8250. Min Act: -0.1700

Data Index: 2645832 (Open Web Text)

Max Activating Token Index: 3