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

Dataset: Open Web Text

Neuron 2233 in Layer 3

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: 3.6913. Min Range: -3.6913

Max Act: 3.6913. Min Act: -0.1700

Data Index: 2265607 (Open Web Text)

Max Activating Token Index: 501

Text #1

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5238. Min Act: -0.1700

Data Index: 6548636 (Open Web Text)

Max Activating Token Index: 106

Text #2

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5134. Min Act: -0.1700

Data Index: 7780158 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5099. Min Act: -0.1700

Data Index: 140655 (Open Web Text)

Max Activating Token Index: 818

Text #4

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5042. Min Act: -0.1700

Data Index: 3466794 (Open Web Text)

Max Activating Token Index: 659

Text #5

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5044. Min Act: -0.1700

Data Index: 622040 (Open Web Text)

Max Activating Token Index: 857

Text #6

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.4867. Min Act: -0.1700

Data Index: 6481975 (Open Web Text)

Max Activating Token Index: 340

Text #7

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.4334. Min Act: -0.1700

Data Index: 4119087 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.4359. Min Act: -0.1700

Data Index: 2282879 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.4065. Min Act: -0.1700

Data Index: 961083 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.4298. Min Act: -0.1700

Data Index: 7039791 (Open Web Text)

Max Activating Token Index: 174

Text #11

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3936. Min Act: -0.1700

Data Index: 8295168 (Open Web Text)

Max Activating Token Index: 671

Text #12

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3995. Min Act: -0.1700

Data Index: 4160686 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3766. Min Act: -0.1700

Data Index: 7542949 (Open Web Text)

Max Activating Token Index: 88

Text #14

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3920. Min Act: -0.1700

Data Index: 1501158 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3571. Min Act: -0.1700

Data Index: 4654702 (Open Web Text)

Max Activating Token Index: 88

Text #16

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3830. Min Act: -0.1700

Data Index: 5586011 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3771. Min Act: -0.1700

Data Index: 4753346 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3619. Min Act: -0.1700

Data Index: 5227205 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3730. Min Act: -0.1700

Data Index: 4065430 (Open Web Text)

Max Activating Token Index: 26