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

Dataset: Open Web Text

Neuron 1282 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: 4.8708. Min Range: -4.8708

Max Act: 4.8708. Min Act: -0.1700

Data Index: 2902406 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.8284. Min Act: -0.1700

Data Index: 236743 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.8138. Min Act: -0.1700

Data Index: 60431 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.8075. Min Act: -0.1700

Data Index: 2848400 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.8076. Min Act: -0.1700

Data Index: 2888047 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7835. Min Act: -0.1700

Data Index: 34836 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7750. Min Act: -0.1700

Data Index: 7473537 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7667. Min Act: -0.1700

Data Index: 2668500 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7808. Min Act: -0.1700

Data Index: 2569788 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7692. Min Act: -0.1700

Data Index: 4838899 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7567. Min Act: -0.1700

Data Index: 3216701 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7439. Min Act: -0.1700

Data Index: 4083461 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7745. Min Act: -0.1700

Data Index: 4074004 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7496. Min Act: -0.1700

Data Index: 2940573 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7526. Min Act: -0.1700

Data Index: 933194 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7124. Min Act: -0.1700

Data Index: 3587659 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7292. Min Act: -0.1700

Data Index: 3902340 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7384. Min Act: -0.1700

Data Index: 4038876 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7263. Min Act: -0.1700

Data Index: 2446446 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.7187. Min Act: -0.1700

Data Index: 2533796 (Open Web Text)

Max Activating Token Index: 8