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

Dataset: Open Web Text

Neuron 850 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: 4.0023. Min Range: -4.0023

Max Act: 3.9699. Min Act: -0.1700

Data Index: 6666030 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9515. Min Act: -0.1700

Data Index: 1047409 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 4.0023. Min Range: -4.0023

Max Act: 4.0023. Min Act: -0.1700

Data Index: 5955615 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9024. Min Act: -0.1700

Data Index: 2814799 (Open Web Text)

Max Activating Token Index: 478

Text #4

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9280. Min Act: -0.1700

Data Index: 6176341 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9465. Min Act: -0.1700

Data Index: 779157 (Open Web Text)

Max Activating Token Index: 713

Text #6

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9096. Min Act: -0.1700

Data Index: 4027730 (Open Web Text)

Max Activating Token Index: 1001

Text #7

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9199. Min Act: -0.1700

Data Index: 560750 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9074. Min Act: -0.1700

Data Index: 2457186 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9058. Min Act: -0.1700

Data Index: 4092393 (Open Web Text)

Max Activating Token Index: 105

Text #10

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.9038. Min Act: -0.1700

Data Index: 6722187 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8915. Min Act: -0.1700

Data Index: 6592226 (Open Web Text)

Max Activating Token Index: 276

Text #12

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8662. Min Act: -0.1700

Data Index: 2417345 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8751. Min Act: -0.1700

Data Index: 4123675 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8838. Min Act: -0.1700

Data Index: 347850 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8464. Min Act: -0.1700

Data Index: 4671807 (Open Web Text)

Max Activating Token Index: 612

Text #16

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8853. Min Act: -0.1700

Data Index: 229652 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8635. Min Act: -0.1700

Data Index: 4894831 (Open Web Text)

Max Activating Token Index: 1003

Text #18

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8969. Min Act: -0.1700

Data Index: 2494647 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 4.0023. Min Range: -4.0023

Max Act: 3.8392. Min Act: -0.1700

Data Index: 5218367 (Open Web Text)

Max Activating Token Index: 509