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

Dataset: Open Web Text

Neuron 1798 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: 1.7747. Min Range: -1.7747

Max Act: 1.7747. Min Act: -0.1690

Data Index: 1944631 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7747. Min Act: -0.1660

Data Index: 7990340 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7747. Min Act: -0.1687

Data Index: 8617296 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7747. Min Act: -0.1678

Data Index: 937883 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7747. Min Act: -0.1688

Data Index: 6150100 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7563. Min Act: -0.1631

Data Index: 3901683 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7591. Min Act: -0.1600

Data Index: 148140 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7465. Min Act: -0.1700

Data Index: 3222366 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7379. Min Act: -0.1653

Data Index: 889992 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7341. Min Act: -0.1686

Data Index: 8435148 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7271. Min Act: -0.1696

Data Index: 6402371 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7263. Min Act: -0.1678

Data Index: 6358682 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7188. Min Act: -0.1401

Data Index: 2987371 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7140. Min Act: -0.1700

Data Index: 1870160 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7037. Min Act: -0.1680

Data Index: 387882 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7071. Min Act: -0.1700

Data Index: 1671532 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7045. Min Act: -0.1619

Data Index: 58488 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7083. Min Act: -0.1700

Data Index: 5372051 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7042. Min Act: -0.1494

Data Index: 5286900 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 1.7747. Min Range: -1.7747

Max Act: 1.7037. Min Act: -0.1548

Data Index: 4775891 (Open Web Text)

Max Activating Token Index: 3