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

Dataset: Open Web Text

Neuron 2730 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: 3.7238. Min Range: -3.7238

Max Act: 3.7238. Min Act: -0.1700

Data Index: 6170418 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6562. Min Act: -0.1700

Data Index: 4323730 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6670. Min Act: -0.1700

Data Index: 4211806 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6564. Min Act: -0.1700

Data Index: 5908722 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6503. Min Act: -0.1700

Data Index: 6721433 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6361. Min Act: -0.1700

Data Index: 4426350 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6186. Min Act: -0.1700

Data Index: 298910 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6258. Min Act: -0.1700

Data Index: 6351491 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6341. Min Act: -0.1700

Data Index: 7864771 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5890. Min Act: -0.1700

Data Index: 6400883 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5953. Min Act: -0.1700

Data Index: 8032034 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5882. Min Act: -0.1700

Data Index: 7844532 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5882. Min Act: -0.1700

Data Index: 7333901 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5888. Min Act: -0.1700

Data Index: 1621463 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6035. Min Act: -0.1700

Data Index: 505542 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.6127. Min Act: -0.1700

Data Index: 5715020 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5914. Min Act: -0.1700

Data Index: 5357755 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5734. Min Act: -0.1700

Data Index: 5935180 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5577. Min Act: -0.1700

Data Index: 5992469 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.7238. Min Range: -3.7238

Max Act: 3.5748. Min Act: -0.1700

Data Index: 1364504 (Open Web Text)

Max Activating Token Index: 5