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

Dataset: Open Web Text

Neuron 51 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: 6.0246. Min Range: -6.0246

Max Act: 6.0246. Min Act: -0.1700

Data Index: 163657 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.8898. Min Act: -0.1700

Data Index: 2960432 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.8640. Min Act: -0.1700

Data Index: 2993713 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.8712. Min Act: -0.1700

Data Index: 4139495 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.8199. Min Act: -0.1700

Data Index: 3121847 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.8488. Min Act: -0.1700

Data Index: 7333248 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.7227. Min Act: -0.1700

Data Index: 4669667 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.7370. Min Act: -0.1700

Data Index: 7961336 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.7102. Min Act: -0.1700

Data Index: 4115012 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.7158. Min Act: -0.1700

Data Index: 7702258 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6960. Min Act: -0.1700

Data Index: 6816998 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6865. Min Act: -0.1700

Data Index: 1776665 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6828. Min Act: -0.1700

Data Index: 736022 (Open Web Text)

Max Activating Token Index: 275

Text #13

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6810. Min Act: -0.1700

Data Index: 2940822 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6679. Min Act: -0.1700

Data Index: 7858900 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6638. Min Act: -0.1700

Data Index: 7506834 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6452. Min Act: -0.1700

Data Index: 6646993 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6558. Min Act: -0.1700

Data Index: 6616015 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6676. Min Act: -0.1700

Data Index: 850025 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 6.0246. Min Range: -6.0246

Max Act: 5.6376. Min Act: -0.1700

Data Index: 1958787 (Open Web Text)

Max Activating Token Index: 12