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

Dataset: Open Web Text

Neuron 2130 in Layer 4

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: 3.3963. Min Range: -3.3963

Max Act: 3.3963. Min Act: -0.1700

Data Index: 4198899 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3899. Min Act: -0.1700

Data Index: 5404117 (Open Web Text)

Max Activating Token Index: 980

Text #2

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3749. Min Act: -0.1700

Data Index: 7513903 (Open Web Text)

Max Activating Token Index: 310

Text #3

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3648. Min Act: -0.1700

Data Index: 2992290 (Open Web Text)

Max Activating Token Index: 60

Text #4

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3077. Min Act: -0.1700

Data Index: 8622861 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2896. Min Act: -0.1700

Data Index: 8197031 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2383. Min Act: -0.1700

Data Index: 3583078 (Open Web Text)

Max Activating Token Index: 319

Text #7

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2796. Min Act: -0.1700

Data Index: 5316531 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2009. Min Act: -0.1700

Data Index: 3204538 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.1174. Min Act: -0.1700

Data Index: 6910940 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.1350. Min Act: -0.1700

Data Index: 3071302 (Open Web Text)

Max Activating Token Index: 784

Text #11

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.1204. Min Act: -0.1700

Data Index: 4561277 (Open Web Text)

Max Activating Token Index: 810

Text #12

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.1133. Min Act: -0.1700

Data Index: 3274687 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.1053. Min Act: -0.1700

Data Index: 5472314 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.0976. Min Act: -0.1700

Data Index: 2785917 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.0834. Min Act: -0.1700

Data Index: 4794868 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.0675. Min Act: -0.1700

Data Index: 1521159 (Open Web Text)

Max Activating Token Index: 646

Text #17

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.0754. Min Act: -0.1700

Data Index: 515718 (Open Web Text)

Max Activating Token Index: 351

Text #18

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.0732. Min Act: -0.1700

Data Index: 4258216 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.0570. Min Act: -0.1700

Data Index: 4532681 (Open Web Text)

Max Activating Token Index: 845