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

Dataset: Open Web Text

Neuron 2908 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: 3.8584. Min Range: -3.8584

Max Act: 3.8404. Min Act: -0.1700

Data Index: 6477543 (Open Web Text)

Max Activating Token Index: 885

Text #1

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.8311. Min Act: -0.1700

Data Index: 7775601 (Open Web Text)

Max Activating Token Index: 331

Text #2

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.8241. Min Act: -0.1700

Data Index: 3142555 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.8584. Min Act: -0.1700

Data Index: 1031754 (Open Web Text)

Max Activating Token Index: 863

Text #4

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.8014. Min Act: -0.1700

Data Index: 5626623 (Open Web Text)

Max Activating Token Index: 848

Text #5

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.8131. Min Act: -0.1700

Data Index: 327948 (Open Web Text)

Max Activating Token Index: 627

Text #6

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.8207. Min Act: -0.1700

Data Index: 7719260 (Open Web Text)

Max Activating Token Index: 921

Text #7

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.8093. Min Act: -0.1700

Data Index: 1007456 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7849. Min Act: -0.1700

Data Index: 4897483 (Open Web Text)

Max Activating Token Index: 176

Text #9

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7826. Min Act: -0.1700

Data Index: 50424 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7527. Min Act: -0.1700

Data Index: 2214819 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7768. Min Act: -0.1700

Data Index: 662330 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7619. Min Act: -0.1700

Data Index: 2029023 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7535. Min Act: -0.1700

Data Index: 2163649 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7558. Min Act: -0.1700

Data Index: 1058952 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7692. Min Act: -0.1700

Data Index: 2062903 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7465. Min Act: -0.1700

Data Index: 766517 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7575. Min Act: -0.1700

Data Index: 2061432 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7596. Min Act: -0.1700

Data Index: 3221485 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 3.8584. Min Range: -3.8584

Max Act: 3.7527. Min Act: -0.1700

Data Index: 2873144 (Open Web Text)

Max Activating Token Index: 165