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

Dataset: Open Web Text

Neuron 979 in Layer 0

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: 4.9454. Min Range: -4.9454

Max Act: 4.9454. Min Act: -0.1700

Data Index: 3932940 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.9234. Min Act: -0.1700

Data Index: 1332720 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8656. Min Act: -0.1700

Data Index: 5326331 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8096. Min Act: -0.1700

Data Index: 7851772 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8294. Min Act: -0.1700

Data Index: 774912 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8237. Min Act: -0.1700

Data Index: 8046286 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8259. Min Act: -0.1700

Data Index: 3607387 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8042. Min Act: -0.1700

Data Index: 4555495 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8204. Min Act: -0.1700

Data Index: 4269528 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8158. Min Act: -0.1700

Data Index: 563561 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7883. Min Act: -0.1700

Data Index: 3784329 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7862. Min Act: -0.1700

Data Index: 6797341 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7927. Min Act: -0.1700

Data Index: 1788746 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7988. Min Act: -0.1700

Data Index: 3156564 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7820. Min Act: -0.1700

Data Index: 2234845 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.8117. Min Act: -0.1700

Data Index: 4142009 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7506. Min Act: -0.1700

Data Index: 162610 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7470. Min Act: -0.1700

Data Index: 6759845 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7582. Min Act: -0.1700

Data Index: 6272389 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.9454. Min Range: -4.9454

Max Act: 4.7759. Min Act: -0.1700

Data Index: 6964359 (Open Web Text)

Max Activating Token Index: 6