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

Dataset: Open Web Text

Neuron 1767 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: 4.9561. Min Range: -4.9561

Max Act: 4.9561. Min Act: -0.1700

Data Index: 8297861 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.9509. Min Act: -0.1700

Data Index: 3354308 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.9106. Min Act: -0.1700

Data Index: 4071437 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.9224. Min Act: -0.1700

Data Index: 6992973 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8968. Min Act: -0.1700

Data Index: 6227503 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8899. Min Act: -0.1700

Data Index: 1437216 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8810. Min Act: -0.1700

Data Index: 4734493 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8780. Min Act: -0.1700

Data Index: 309186 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8673. Min Act: -0.1700

Data Index: 844841 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8630. Min Act: -0.1700

Data Index: 4066167 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8594. Min Act: -0.1700

Data Index: 7037047 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8531. Min Act: -0.1700

Data Index: 7724710 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8604. Min Act: -0.1700

Data Index: 2468637 (Open Web Text)

Max Activating Token Index: 241

Text #13

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8069. Min Act: -0.1700

Data Index: 6026898 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8236. Min Act: -0.1700

Data Index: 7002121 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8050. Min Act: -0.1700

Data Index: 1513561 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8381. Min Act: -0.1700

Data Index: 5504869 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8227. Min Act: -0.1700

Data Index: 8012764 (Open Web Text)

Max Activating Token Index: 269

Text #18

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8219. Min Act: -0.1700

Data Index: 4500128 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.9561. Min Range: -4.9561

Max Act: 4.8372. Min Act: -0.1700

Data Index: 1272232 (Open Web Text)

Max Activating Token Index: 664