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

Dataset: Open Web Text

Neuron 1466 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: 4.0843. Min Range: -4.0843

Max Act: 4.0843. Min Act: -0.1700

Data Index: 5794816 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0497. Min Act: -0.1700

Data Index: 5384484 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0447. Min Act: -0.1700

Data Index: 1944556 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0556. Min Act: -0.1700

Data Index: 6271664 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0549. Min Act: -0.1700

Data Index: 7404407 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0635. Min Act: -0.1700

Data Index: 3445773 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0635. Min Act: -0.1700

Data Index: 3193922 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0635. Min Act: -0.1700

Data Index: 5071287 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.9961. Min Act: -0.1700

Data Index: 1843606 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0142. Min Act: -0.1700

Data Index: 3637916 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0211. Min Act: -0.1700

Data Index: 3869435 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0152. Min Act: -0.1700

Data Index: 4887408 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.9991. Min Act: -0.1700

Data Index: 1581247 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0099. Min Act: -0.1700

Data Index: 553518 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 4.0843. Min Range: -4.0843

Max Act: 4.0004. Min Act: -0.1700

Data Index: 1714300 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.9830. Min Act: -0.1700

Data Index: 3128558 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.9844. Min Act: -0.1700

Data Index: 1629241 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.9812. Min Act: -0.1700

Data Index: 2328244 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.9865. Min Act: -0.1700

Data Index: 3105817 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0843. Min Range: -4.0843

Max Act: 3.9697. Min Act: -0.1700

Data Index: 2755329 (Open Web Text)

Max Activating Token Index: 7