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

Dataset: Open Web Text

Neuron 2698 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: 2.9517. Min Range: -2.9517

Max Act: 2.9517. Min Act: -0.1700

Data Index: 1079618 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.9284. Min Act: -0.1700

Data Index: 999885 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.9060. Min Act: -0.1700

Data Index: 922053 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.9170. Min Act: -0.1700

Data Index: 4480654 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.9165. Min Act: -0.1700

Data Index: 4033030 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8923. Min Act: -0.1700

Data Index: 7995837 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8998. Min Act: -0.1700

Data Index: 6369795 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.9040. Min Act: -0.1700

Data Index: 1448247 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.9053. Min Act: -0.1700

Data Index: 2977603 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8789. Min Act: -0.1700

Data Index: 2420129 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8826. Min Act: -0.1700

Data Index: 2192078 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8853. Min Act: -0.1700

Data Index: 5014709 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8652. Min Act: -0.1700

Data Index: 4950438 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8711. Min Act: -0.1700

Data Index: 1609490 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8661. Min Act: -0.1700

Data Index: 3554813 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8445. Min Act: -0.1700

Data Index: 3450255 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8467. Min Act: -0.1700

Data Index: 4667865 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8507. Min Act: -0.1700

Data Index: 6096106 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8485. Min Act: -0.1700

Data Index: 3389689 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.9517. Min Range: -2.9517

Max Act: 2.8570. Min Act: -0.1700

Data Index: 452482 (Open Web Text)

Max Activating Token Index: 3