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

Dataset: Open Web Text

Neuron 1182 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: 4.0654. Min Range: -4.0654

Max Act: 4.0654. Min Act: -0.1700

Data Index: 4365462 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0583. Min Act: -0.1700

Data Index: 6050650 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0324. Min Act: -0.1700

Data Index: 8472546 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0540. Min Act: -0.1700

Data Index: 1113020 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0010. Min Act: -0.1700

Data Index: 7592196 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9931. Min Act: -0.1700

Data Index: 1677593 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0049. Min Act: -0.1700

Data Index: 2696667 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0090. Min Act: -0.1700

Data Index: 5573882 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0032. Min Act: -0.1700

Data Index: 7224501 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9726. Min Act: -0.1700

Data Index: 6526083 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9768. Min Act: -0.1700

Data Index: 7402874 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9679. Min Act: -0.1700

Data Index: 5777349 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9904. Min Act: -0.1700

Data Index: 1051446 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9684. Min Act: -0.1700

Data Index: 5643342 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9812. Min Act: -0.1700

Data Index: 7986345 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9541. Min Act: -0.1700

Data Index: 5669356 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9396. Min Act: -0.1700

Data Index: 4788908 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9446. Min Act: -0.1700

Data Index: 6271214 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9455. Min Act: -0.1700

Data Index: 5883045 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.9421. Min Act: -0.1700

Data Index: 594444 (Open Web Text)

Max Activating Token Index: 25