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

Dataset: Open Web Text

Neuron 1972 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: 3.9902. Min Range: -3.9902

Max Act: 3.9902. Min Act: -0.1700

Data Index: 3512114 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.9566. Min Act: -0.1700

Data Index: 1062951 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8996. Min Act: -0.1700

Data Index: 7228020 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.9238. Min Act: -0.1700

Data Index: 5202584 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8720. Min Act: -0.1700

Data Index: 5266867 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8624. Min Act: -0.1700

Data Index: 6490592 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8716. Min Act: -0.1700

Data Index: 2220950 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8840. Min Act: -0.1700

Data Index: 8296953 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8509. Min Act: -0.1700

Data Index: 5822646 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8422. Min Act: -0.1700

Data Index: 2926565 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8340. Min Act: -0.1700

Data Index: 4952662 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8377. Min Act: -0.1700

Data Index: 7623928 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8366. Min Act: -0.1700

Data Index: 5848362 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8480. Min Act: -0.1700

Data Index: 3824714 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8044. Min Act: -0.1700

Data Index: 237923 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.7730. Min Act: -0.1700

Data Index: 5186745 (Open Web Text)

Max Activating Token Index: 936

Text #16

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.7950. Min Act: -0.1700

Data Index: 3782622 (Open Web Text)

Max Activating Token Index: 826

Text #17

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8245. Min Act: -0.1700

Data Index: 5233939 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8048. Min Act: -0.1700

Data Index: 609797 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.9902. Min Range: -3.9902

Max Act: 3.8011. Min Act: -0.1700

Data Index: 5279342 (Open Web Text)

Max Activating Token Index: 1020