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

Dataset: Open Web Text

Neuron 1715 in Layer 6

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: 5.0556. Min Range: -5.0556

Max Act: 5.0482. Min Act: -0.1700

Data Index: 2769156 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 5.0556. Min Range: -5.0556

Max Act: 5.0556. Min Act: -0.1700

Data Index: 5206994 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9645. Min Act: -0.1700

Data Index: 5369526 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9845. Min Act: -0.1700

Data Index: 8739085 (Open Web Text)

Max Activating Token Index: 242

Text #4

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9521. Min Act: -0.1700

Data Index: 1145618 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9619. Min Act: -0.1700

Data Index: 800635 (Open Web Text)

Max Activating Token Index: 904

Text #6

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9728. Min Act: -0.1700

Data Index: 1246998 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9404. Min Act: -0.1700

Data Index: 5364813 (Open Web Text)

Max Activating Token Index: 915

Text #8

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9440. Min Act: -0.1700

Data Index: 4133968 (Open Web Text)

Max Activating Token Index: 819

Text #9

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9402. Min Act: -0.1700

Data Index: 1748620 (Open Web Text)

Max Activating Token Index: 943

Text #10

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9341. Min Act: -0.1700

Data Index: 5723765 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9419. Min Act: -0.1700

Data Index: 976499 (Open Web Text)

Max Activating Token Index: 128

Text #12

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9184. Min Act: -0.1700

Data Index: 2377391 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.8714. Min Act: -0.1700

Data Index: 2091709 (Open Web Text)

Max Activating Token Index: 95

Text #14

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.8872. Min Act: -0.1700

Data Index: 6265370 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.8882. Min Act: -0.1700

Data Index: 2732021 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.8869. Min Act: -0.1700

Data Index: 3737936 (Open Web Text)

Max Activating Token Index: 809

Text #17

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.8662. Min Act: -0.1700

Data Index: 2339805 (Open Web Text)

Max Activating Token Index: 845

Text #18

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.8370. Min Act: -0.1700

Data Index: 2177131 (Open Web Text)

Max Activating Token Index: 637

Text #19

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.8709. Min Act: -0.1700

Data Index: 5552848 (Open Web Text)

Max Activating Token Index: 127