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

Dataset: Open Web Text

Neuron 1722 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: 3.3538. Min Range: -3.3538

Max Act: 3.3538. Min Act: -0.1700

Data Index: 368760 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.3314. Min Act: -0.1700

Data Index: 5951547 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2621. Min Act: -0.1700

Data Index: 3244511 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2531. Min Act: -0.1700

Data Index: 3797736 (Open Web Text)

Max Activating Token Index: 37

Text #4

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2363. Min Act: -0.1700

Data Index: 7459332 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2366. Min Act: -0.1700

Data Index: 3148570 (Open Web Text)

Max Activating Token Index: 29

Text #6

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2087. Min Act: -0.1700

Data Index: 5794756 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.2011. Min Act: -0.1700

Data Index: 3084544 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1940. Min Act: -0.1700

Data Index: 3079568 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1759. Min Act: -0.1700

Data Index: 1798488 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1807. Min Act: -0.1700

Data Index: 5841012 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1876. Min Act: -0.1700

Data Index: 3582005 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1732. Min Act: -0.1700

Data Index: 7539199 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1720. Min Act: -0.1700

Data Index: 3582003 (Open Web Text)

Max Activating Token Index: 234

Text #14

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1660. Min Act: -0.1700

Data Index: 7054545 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1696. Min Act: -0.1700

Data Index: 2291037 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1746. Min Act: -0.1700

Data Index: 492914 (Open Web Text)

Max Activating Token Index: 993

Text #17

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1705. Min Act: -0.1700

Data Index: 3092271 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1675. Min Act: -0.1700

Data Index: 6092918 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 3.3538. Min Range: -3.3538

Max Act: 3.1677. Min Act: -0.1700

Data Index: 1516925 (Open Web Text)

Max Activating Token Index: 297