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

Dataset: Open Web Text

Neuron 1233 in Layer 5

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: 2.7944. Min Range: -2.7944

Max Act: 2.7944. Min Act: -0.1700

Data Index: 1665100 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.7536. Min Act: -0.1700

Data Index: 6168033 (Open Web Text)

Max Activating Token Index: 970

Text #2

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.6912. Min Act: -0.1700

Data Index: 5985580 (Open Web Text)

Max Activating Token Index: 338

Text #3

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.7328. Min Act: -0.1700

Data Index: 602284 (Open Web Text)

Max Activating Token Index: 419

Text #4

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.6623. Min Act: -0.1700

Data Index: 1414556 (Open Web Text)

Max Activating Token Index: 945

Text #5

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.6236. Min Act: -0.1700

Data Index: 7991394 (Open Web Text)

Max Activating Token Index: 737

Text #6

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.6364. Min Act: -0.1700

Data Index: 3393058 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.6259. Min Act: -0.1700

Data Index: 5379835 (Open Web Text)

Max Activating Token Index: 881

Text #8

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5980. Min Act: -0.1700

Data Index: 6747716 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.6093. Min Act: -0.1700

Data Index: 4692373 (Open Web Text)

Max Activating Token Index: 632

Text #10

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.6117. Min Act: -0.1700

Data Index: 3544098 (Open Web Text)

Max Activating Token Index: 155

Text #11

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5965. Min Act: -0.1700

Data Index: 7133806 (Open Web Text)

Max Activating Token Index: 921

Text #12

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5909. Min Act: -0.1700

Data Index: 6366856 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5896. Min Act: -0.1700

Data Index: 1918012 (Open Web Text)

Max Activating Token Index: 185

Text #14

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5921. Min Act: -0.1700

Data Index: 7435602 (Open Web Text)

Max Activating Token Index: 536

Text #15

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5915. Min Act: -0.1700

Data Index: 2699390 (Open Web Text)

Max Activating Token Index: 490

Text #16

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5999. Min Act: -0.1700

Data Index: 5412066 (Open Web Text)

Max Activating Token Index: 210

Text #17

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5794. Min Act: -0.1700

Data Index: 4586615 (Open Web Text)

Max Activating Token Index: 508

Text #18

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5739. Min Act: -0.1700

Data Index: 4333794 (Open Web Text)

Max Activating Token Index: 249

Text #19

Max Range: 2.7944. Min Range: -2.7944

Max Act: 2.5930. Min Act: -0.1700

Data Index: 632172 (Open Web Text)

Max Activating Token Index: 50