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

Dataset: Open Web Text

Neuron 2725 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: 3.0636. Min Range: -3.0636

Max Act: 3.0636. Min Act: -0.1700

Data Index: 5390555 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0448. Min Act: -0.1700

Data Index: 5945817 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0114. Min Act: -0.1700

Data Index: 6432565 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9986. Min Act: -0.1700

Data Index: 6522757 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0001. Min Act: -0.1700

Data Index: 682968 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0001. Min Act: -0.1700

Data Index: 3277657 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0000. Min Act: -0.1700

Data Index: 1824838 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.0636. Min Range: -3.0636

Max Act: 3.0001. Min Act: -0.1700

Data Index: 6988212 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9976. Min Act: -0.1700

Data Index: 3776811 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9838. Min Act: -0.1700

Data Index: 4776576 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9861. Min Act: -0.1700

Data Index: 5250466 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9838. Min Act: -0.1700

Data Index: 3365461 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9838. Min Act: -0.1700

Data Index: 5758436 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9637. Min Act: -0.1700

Data Index: 3705633 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9627. Min Act: -0.1700

Data Index: 6070499 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9701. Min Act: -0.1700

Data Index: 1913829 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9605. Min Act: -0.1700

Data Index: 4342037 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9596. Min Act: -0.1700

Data Index: 1207389 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9483. Min Act: -0.1700

Data Index: 2268680 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.0636. Min Range: -3.0636

Max Act: 2.9362. Min Act: -0.1700

Data Index: 4113166 (Open Web Text)

Max Activating Token Index: 6