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

Dataset: Open Web Text

Neuron 2994 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: 4.0994. Min Range: -4.0994

Max Act: 4.0994. Min Act: -0.1700

Data Index: 8715120 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.0994. Min Range: -4.0994

Max Act: 4.0518. Min Act: -0.1700

Data Index: 2020477 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.0994. Min Range: -4.0994

Max Act: 4.0121. Min Act: -0.1700

Data Index: 2690769 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9838. Min Act: -0.1700

Data Index: 3964243 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9486. Min Act: -0.1700

Data Index: 6903856 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9608. Min Act: -0.1700

Data Index: 4999388 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9536. Min Act: -0.1700

Data Index: 5184851 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9454. Min Act: -0.1700

Data Index: 7148280 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9529. Min Act: -0.1700

Data Index: 565371 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9457. Min Act: -0.1700

Data Index: 4586972 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9139. Min Act: -0.1700

Data Index: 6551427 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9359. Min Act: -0.1700

Data Index: 5460207 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.9147. Min Act: -0.1700

Data Index: 1214911 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.8997. Min Act: -0.1700

Data Index: 8320557 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.8652. Min Act: -0.1700

Data Index: 5057262 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.8519. Min Act: -0.1700

Data Index: 4622869 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.8616. Min Act: -0.1700

Data Index: 4493223 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.8539. Min Act: -0.1700

Data Index: 5486784 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.8624. Min Act: -0.1700

Data Index: 5086823 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.8659. Min Act: -0.1700

Data Index: 4192019 (Open Web Text)

Max Activating Token Index: 5