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

Dataset: Open Web Text

Neuron 2548 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: 6.0726. Min Range: -6.0726

Max Act: 6.0726. Min Act: -0.1700

Data Index: 4299975 (Open Web Text)

Max Activating Token Index: 574

Text #1

Max Range: 6.0726. Min Range: -6.0726

Max Act: 6.0366. Min Act: -0.1700

Data Index: 2028864 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 6.0726. Min Range: -6.0726

Max Act: 6.0537. Min Act: -0.1700

Data Index: 2749732 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 6.0726. Min Range: -6.0726

Max Act: 6.0238. Min Act: -0.1700

Data Index: 6102729 (Open Web Text)

Max Activating Token Index: 555

Text #4

Max Range: 6.0726. Min Range: -6.0726

Max Act: 6.0160. Min Act: -0.1700

Data Index: 5149556 (Open Web Text)

Max Activating Token Index: 830

Text #5

Max Range: 6.0726. Min Range: -6.0726

Max Act: 6.0020. Min Act: -0.1700

Data Index: 1320802 (Open Web Text)

Max Activating Token Index: 656

Text #6

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9844. Min Act: -0.1700

Data Index: 6938183 (Open Web Text)

Max Activating Token Index: 244

Text #7

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9637. Min Act: -0.1700

Data Index: 883771 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9321. Min Act: -0.1700

Data Index: 7356072 (Open Web Text)

Max Activating Token Index: 755

Text #9

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9214. Min Act: -0.1700

Data Index: 3972029 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9412. Min Act: -0.1700

Data Index: 8535821 (Open Web Text)

Max Activating Token Index: 383

Text #11

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9205. Min Act: -0.1700

Data Index: 7088336 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9719. Min Act: -0.1700

Data Index: 516482 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.8994. Min Act: -0.1700

Data Index: 3203658 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.8794. Min Act: -0.1700

Data Index: 5677226 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9324. Min Act: -0.1700

Data Index: 4063800 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9384. Min Act: -0.1700

Data Index: 6744045 (Open Web Text)

Max Activating Token Index: 989

Text #17

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.8997. Min Act: -0.1700

Data Index: 5060367 (Open Web Text)

Max Activating Token Index: 689

Text #18

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.9017. Min Act: -0.1700

Data Index: 6252955 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 6.0726. Min Range: -6.0726

Max Act: 5.8670. Min Act: -0.1700

Data Index: 6643610 (Open Web Text)

Max Activating Token Index: 614