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

Dataset: Open Web Text

Neuron 1493 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: 3.5709. Min Range: -3.5709

Max Act: 3.5709. Min Act: -0.1700

Data Index: 643828 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4986. Min Act: -0.1700

Data Index: 7616720 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4749. Min Act: -0.1700

Data Index: 6861867 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4493. Min Act: -0.1700

Data Index: 5958578 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4502. Min Act: -0.1700

Data Index: 3115965 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4695. Min Act: -0.1700

Data Index: 2958347 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4265. Min Act: -0.1700

Data Index: 2122101 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4105. Min Act: -0.1700

Data Index: 6107692 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4224. Min Act: -0.1700

Data Index: 638724 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4208. Min Act: -0.1700

Data Index: 2458172 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4124. Min Act: -0.1700

Data Index: 7183070 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4431. Min Act: -0.1700

Data Index: 2424868 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4119. Min Act: -0.1700

Data Index: 5037714 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4239. Min Act: -0.1700

Data Index: 2317438 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4184. Min Act: -0.1700

Data Index: 6653745 (Open Web Text)

Max Activating Token Index: 1009

Text #15

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4404. Min Act: -0.1700

Data Index: 2670283 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4192. Min Act: -0.1700

Data Index: 3956536 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4201. Min Act: -0.1700

Data Index: 3506170 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.4091. Min Act: -0.1700

Data Index: 2515323 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.5709. Min Range: -3.5709

Max Act: 3.3995. Min Act: -0.1700

Data Index: 1293132 (Open Web Text)

Max Activating Token Index: 5