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

Dataset: Open Web Text

Neuron 2982 in Layer 1

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: 1.7252. Min Range: -1.7252

Max Act: 1.7252. Min Act: -0.1700

Data Index: 204473 (Open Web Text)

Max Activating Token Index: 82

Text #1

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6992. Min Act: -0.1700

Data Index: 4745917 (Open Web Text)

Max Activating Token Index: 41

Text #2

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6732. Min Act: -0.1642

Data Index: 4052912 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6390. Min Act: -0.1700

Data Index: 8264991 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6475. Min Act: -0.1640

Data Index: 4079985 (Open Web Text)

Max Activating Token Index: 249

Text #5

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6396. Min Act: -0.1687

Data Index: 6297536 (Open Web Text)

Max Activating Token Index: 54

Text #6

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6467. Min Act: -0.1700

Data Index: 5218463 (Open Web Text)

Max Activating Token Index: 38

Text #7

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6413. Min Act: -0.1700

Data Index: 7755963 (Open Web Text)

Max Activating Token Index: 221

Text #8

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6149. Min Act: -0.1687

Data Index: 3698631 (Open Web Text)

Max Activating Token Index: 321

Text #9

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6184. Min Act: -0.1700

Data Index: 3805591 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6169. Min Act: -0.1700

Data Index: 1140827 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6141. Min Act: -0.1700

Data Index: 7636146 (Open Web Text)

Max Activating Token Index: 233

Text #12

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6051. Min Act: -0.1700

Data Index: 7144338 (Open Web Text)

Max Activating Token Index: 42

Text #13

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.5955. Min Act: -0.1700

Data Index: 4265319 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.6019. Min Act: -0.1700

Data Index: 1500496 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.5948. Min Act: -0.1700

Data Index: 566706 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.5926. Min Act: -0.1700

Data Index: 5891150 (Open Web Text)

Max Activating Token Index: 117

Text #17

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.5879. Min Act: -0.1659

Data Index: 7529003 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.5844. Min Act: -0.1677

Data Index: 6068919 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 1.7252. Min Range: -1.7252

Max Act: 1.5891. Min Act: -0.1700

Data Index: 2736586 (Open Web Text)

Max Activating Token Index: 19