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

Dataset: Open Web Text

Neuron 2015 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: 0.9082. Min Range: -0.9082

Max Act: 0.9082. Min Act: -0.1700

Data Index: 1280783 (Open Web Text)

Max Activating Token Index: 179

Text #1

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8649. Min Act: -0.1700

Data Index: 595698 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8676. Min Act: -0.1700

Data Index: 4274322 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8713. Min Act: -0.1700

Data Index: 5307648 (Open Web Text)

Max Activating Token Index: 165

Text #4

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8378. Min Act: -0.1700

Data Index: 1413673 (Open Web Text)

Max Activating Token Index: 167

Text #5

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8424. Min Act: -0.1700

Data Index: 5955305 (Open Web Text)

Max Activating Token Index: 171

Text #6

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8464. Min Act: -0.1700

Data Index: 8424043 (Open Web Text)

Max Activating Token Index: 173

Text #7

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8300. Min Act: -0.1700

Data Index: 8121628 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8428. Min Act: -0.1700

Data Index: 3356143 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.8290. Min Act: -0.1700

Data Index: 6619245 (Open Web Text)

Max Activating Token Index: 156

Text #10

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7923. Min Act: -0.1700

Data Index: 689547 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7961. Min Act: -0.1700

Data Index: 1422595 (Open Web Text)

Max Activating Token Index: 174

Text #12

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7838. Min Act: -0.1700

Data Index: 3031034 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7759. Min Act: -0.1700

Data Index: 3353486 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7744. Min Act: -0.1700

Data Index: 5546979 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7710. Min Act: -0.1700

Data Index: 4799921 (Open Web Text)

Max Activating Token Index: 216

Text #16

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7745. Min Act: -0.1700

Data Index: 5052394 (Open Web Text)

Max Activating Token Index: 187

Text #17

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7563. Min Act: -0.1700

Data Index: 6402956 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7664. Min Act: -0.1700

Data Index: 4564439 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 0.9082. Min Range: -0.9082

Max Act: 0.7629. Min Act: -0.1700

Data Index: 2347376 (Open Web Text)

Max Activating Token Index: 159