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

Dataset: Open Web Text

Neuron 1640 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: 3.9476. Min Range: -3.9476

Max Act: 3.9476. Min Act: -0.1700

Data Index: 6312652 (Open Web Text)

Max Activating Token Index: 432

Text #1

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.8921. Min Act: -0.1700

Data Index: 3060606 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.8576. Min Act: -0.1700

Data Index: 3132510 (Open Web Text)

Max Activating Token Index: 106

Text #3

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.8667. Min Act: -0.1700

Data Index: 5746552 (Open Web Text)

Max Activating Token Index: 95

Text #4

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.8249. Min Act: -0.1700

Data Index: 4403009 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.8214. Min Act: -0.1700

Data Index: 8070287 (Open Web Text)

Max Activating Token Index: 165

Text #6

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7786. Min Act: -0.1700

Data Index: 6591177 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7804. Min Act: -0.1700

Data Index: 7913705 (Open Web Text)

Max Activating Token Index: 472

Text #8

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.8064. Min Act: -0.1700

Data Index: 89508 (Open Web Text)

Max Activating Token Index: 384

Text #9

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7475. Min Act: -0.1700

Data Index: 2364000 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7649. Min Act: -0.1700

Data Index: 4780183 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7648. Min Act: -0.1700

Data Index: 7223342 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.8148. Min Act: -0.1700

Data Index: 2354373 (Open Web Text)

Max Activating Token Index: 615

Text #13

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7758. Min Act: -0.1700

Data Index: 1876683 (Open Web Text)

Max Activating Token Index: 588

Text #14

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7754. Min Act: -0.1700

Data Index: 4544866 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7790. Min Act: -0.1700

Data Index: 3397877 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7669. Min Act: -0.1700

Data Index: 5726617 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7855. Min Act: -0.1700

Data Index: 5094886 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7830. Min Act: -0.1700

Data Index: 5060619 (Open Web Text)

Max Activating Token Index: 357

Text #19

Max Range: 3.9476. Min Range: -3.9476

Max Act: 3.7782. Min Act: -0.1700

Data Index: 4967902 (Open Web Text)

Max Activating Token Index: 91