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

Dataset: Open Web Text

Neuron 385 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: 2.9920. Min Range: -2.9920

Max Act: 2.9777. Min Act: -0.1700

Data Index: 7263046 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.9760. Min Act: -0.1700

Data Index: 1803963 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.9920. Min Act: -0.1700

Data Index: 5119463 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.9744. Min Act: -0.1700

Data Index: 2929201 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.9329. Min Act: -0.1700

Data Index: 3784753 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8998. Min Act: -0.1700

Data Index: 5077499 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.9026. Min Act: -0.1700

Data Index: 5989407 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.9058. Min Act: -0.1700

Data Index: 1616018 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8944. Min Act: -0.1700

Data Index: 3405977 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8901. Min Act: -0.1700

Data Index: 6901742 (Open Web Text)

Max Activating Token Index: 851

Text #10

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8921. Min Act: -0.1700

Data Index: 1542396 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.9000. Min Act: -0.1700

Data Index: 1409333 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8810. Min Act: -0.1700

Data Index: 4135479 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8652. Min Act: -0.1700

Data Index: 5275716 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8593. Min Act: -0.1700

Data Index: 6901747 (Open Web Text)

Max Activating Token Index: 831

Text #15

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8735. Min Act: -0.1700

Data Index: 7027679 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8670. Min Act: -0.1700

Data Index: 665368 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8575. Min Act: -0.1700

Data Index: 6901737 (Open Web Text)

Max Activating Token Index: 927

Text #18

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8565. Min Act: -0.1700

Data Index: 7263047 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.9920. Min Range: -2.9920

Max Act: 2.8378. Min Act: -0.1700

Data Index: 6579681 (Open Web Text)

Max Activating Token Index: 853