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

Dataset: Open Web Text

Neuron 1742 in Layer 2

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: 2.5767. Min Range: -2.5767

Max Act: 2.5767. Min Act: -0.1700

Data Index: 4779584 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4988. Min Act: -0.1700

Data Index: 6114430 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4643. Min Act: -0.1700

Data Index: 8585437 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4555. Min Act: -0.1700

Data Index: 381151 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4689. Min Act: -0.1700

Data Index: 3086912 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4433. Min Act: -0.1700

Data Index: 381154 (Open Web Text)

Max Activating Token Index: 942

Text #6

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4555. Min Act: -0.1700

Data Index: 4220469 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4583. Min Act: -0.1700

Data Index: 5958488 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4370. Min Act: -0.1700

Data Index: 6384999 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4328. Min Act: -0.1700

Data Index: 6911138 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4511. Min Act: -0.1700

Data Index: 4132257 (Open Web Text)

Max Activating Token Index: 18

Text #11

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4182. Min Act: -0.1700

Data Index: 7947835 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.4439. Min Act: -0.1700

Data Index: 2543084 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.3900. Min Act: -0.1700

Data Index: 975125 (Open Web Text)

Max Activating Token Index: 525

Text #14

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.3972. Min Act: -0.1700

Data Index: 6711715 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.3965. Min Act: -0.1700

Data Index: 8829991 (Open Web Text)

Max Activating Token Index: 681

Text #16

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.3894. Min Act: -0.1700

Data Index: 5000836 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.3643. Min Act: -0.1700

Data Index: 7084973 (Open Web Text)

Max Activating Token Index: 687

Text #18

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.3875. Min Act: -0.1700

Data Index: 4626497 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.5767. Min Range: -2.5767

Max Act: 2.3764. Min Act: -0.1700

Data Index: 6005937 (Open Web Text)

Max Activating Token Index: 5