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

Dataset: Open Web Text

Neuron 456 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: 3.4075. Min Range: -3.4075

Max Act: 3.4075. Min Act: -0.1700

Data Index: 4409186 (Open Web Text)

Max Activating Token Index: 95

Text #1

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3541. Min Act: -0.1700

Data Index: 83452 (Open Web Text)

Max Activating Token Index: 283

Text #2

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3583. Min Act: -0.1700

Data Index: 7481810 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3361. Min Act: -0.1700

Data Index: 8383752 (Open Web Text)

Max Activating Token Index: 682

Text #4

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3244. Min Act: -0.1700

Data Index: 1084286 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3120. Min Act: -0.1700

Data Index: 2492219 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3079. Min Act: -0.1700

Data Index: 5118956 (Open Web Text)

Max Activating Token Index: 538

Text #7

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3172. Min Act: -0.1700

Data Index: 6209561 (Open Web Text)

Max Activating Token Index: 205

Text #8

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3101. Min Act: -0.1700

Data Index: 2664926 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3122. Min Act: -0.1700

Data Index: 3362455 (Open Web Text)

Max Activating Token Index: 193

Text #10

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.3116. Min Act: -0.1700

Data Index: 1001993 (Open Web Text)

Max Activating Token Index: 824

Text #11

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2781. Min Act: -0.1700

Data Index: 8353871 (Open Web Text)

Max Activating Token Index: 138

Text #12

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2811. Min Act: -0.1700

Data Index: 572947 (Open Web Text)

Max Activating Token Index: 112

Text #13

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2780. Min Act: -0.1700

Data Index: 4727988 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2929. Min Act: -0.1700

Data Index: 8443117 (Open Web Text)

Max Activating Token Index: 199

Text #15

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2783. Min Act: -0.1700

Data Index: 5719430 (Open Web Text)

Max Activating Token Index: 107

Text #16

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2717. Min Act: -0.1700

Data Index: 4924503 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2798. Min Act: -0.1700

Data Index: 5247829 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2841. Min Act: -0.1700

Data Index: 2416969 (Open Web Text)

Max Activating Token Index: 596

Text #19

Max Range: 3.4075. Min Range: -3.4075

Max Act: 3.2767. Min Act: -0.1700

Data Index: 6394171 (Open Web Text)

Max Activating Token Index: 341