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

Dataset: Open Web Text

Neuron 1488 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: 3.9907. Min Range: -3.9907

Max Act: 3.9907. Min Act: -0.1700

Data Index: 6551376 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.9907. Min Act: -0.1700

Data Index: 2115816 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.9907. Min Act: -0.1700

Data Index: 6040489 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.9694. Min Act: -0.1700

Data Index: 6544927 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.9646. Min Act: -0.1700

Data Index: 108345 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8914. Min Act: -0.1700

Data Index: 175752 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.9106. Min Act: -0.1700

Data Index: 44431 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8967. Min Act: -0.1700

Data Index: 3981053 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8914. Min Act: -0.1700

Data Index: 1301740 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8648. Min Act: -0.1700

Data Index: 7570549 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8599. Min Act: -0.1700

Data Index: 7468522 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8848. Min Act: -0.1700

Data Index: 210850 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8764. Min Act: -0.1700

Data Index: 493356 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8447. Min Act: -0.1700

Data Index: 6412639 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8258. Min Act: -0.1700

Data Index: 2409675 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8338. Min Act: -0.1700

Data Index: 6006235 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8331. Min Act: -0.1700

Data Index: 6513662 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8338. Min Act: -0.1700

Data Index: 99348 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8390. Min Act: -0.1700

Data Index: 3619008 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.9907. Min Range: -3.9907

Max Act: 3.8386. Min Act: -0.1700

Data Index: 643274 (Open Web Text)

Max Activating Token Index: 4