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

Dataset: Open Web Text

Neuron 1013 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: 0.5362. Min Range: -0.5362

Max Act: 0.5356. Min Act: -0.1700

Data Index: 7405444 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5362. Min Act: -0.1700

Data Index: 4049785 (Open Web Text)

Max Activating Token Index: 22

Text #2

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5255. Min Act: -0.1700

Data Index: 7769343 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5223. Min Act: -0.1700

Data Index: 4049792 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5244. Min Act: -0.1700

Data Index: 8771332 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5098. Min Act: -0.1700

Data Index: 5046160 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5040. Min Act: -0.1700

Data Index: 3212433 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4998. Min Act: -0.1700

Data Index: 3258803 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5091. Min Act: -0.1700

Data Index: 1131140 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4982. Min Act: -0.1700

Data Index: 6662895 (Open Web Text)

Max Activating Token Index: 19

Text #10

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5023. Min Act: -0.1700

Data Index: 2842723 (Open Web Text)

Max Activating Token Index: 24

Text #11

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4940. Min Act: -0.1700

Data Index: 715144 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4948. Min Act: -0.1700

Data Index: 4893774 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.5000. Min Act: -0.1700

Data Index: 5920700 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4970. Min Act: -0.1700

Data Index: 6137296 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4970. Min Act: -0.1700

Data Index: 4491426 (Open Web Text)

Max Activating Token Index: 20

Text #16

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4934. Min Act: -0.1700

Data Index: 7262648 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4929. Min Act: -0.1700

Data Index: 7360749 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4918. Min Act: -0.1700

Data Index: 327967 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 0.5362. Min Range: -0.5362

Max Act: 0.4912. Min Act: -0.1700

Data Index: 2086628 (Open Web Text)

Max Activating Token Index: 21