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

Dataset: Open Web Text

Neuron 849 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: 3.0503. Min Range: -3.0503

Max Act: 3.0503. Min Act: -0.1700

Data Index: 8750647 (Open Web Text)

Max Activating Token Index: 31

Text #1

Max Range: 3.0503. Min Range: -3.0503

Max Act: 3.0317. Min Act: -0.1700

Data Index: 3780786 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.0503. Min Range: -3.0503

Max Act: 3.0424. Min Act: -0.1700

Data Index: 8227284 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 3.0503. Min Range: -3.0503

Max Act: 3.0126. Min Act: -0.1700

Data Index: 1533882 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9836. Min Act: -0.1700

Data Index: 4804622 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9856. Min Act: -0.1700

Data Index: 5214610 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9725. Min Act: -0.1700

Data Index: 57823 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9665. Min Act: -0.1700

Data Index: 1195877 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9728. Min Act: -0.1700

Data Index: 6476597 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9843. Min Act: -0.1700

Data Index: 6219631 (Open Web Text)

Max Activating Token Index: 483

Text #10

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9745. Min Act: -0.1700

Data Index: 5732452 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9694. Min Act: -0.1700

Data Index: 524622 (Open Web Text)

Max Activating Token Index: 624

Text #12

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9607. Min Act: -0.1700

Data Index: 8739373 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9688. Min Act: -0.1700

Data Index: 7692326 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9499. Min Act: -0.1700

Data Index: 991591 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9568. Min Act: -0.1700

Data Index: 2215891 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9486. Min Act: -0.1700

Data Index: 421855 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9476. Min Act: -0.1700

Data Index: 3293307 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9613. Min Act: -0.1700

Data Index: 6761551 (Open Web Text)

Max Activating Token Index: 388

Text #19

Max Range: 3.0503. Min Range: -3.0503

Max Act: 2.9597. Min Act: -0.1700

Data Index: 2364714 (Open Web Text)

Max Activating Token Index: 12