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

Dataset: Open Web Text

Neuron 1066 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: 4.1041. Min Range: -4.1041

Max Act: 4.1041. Min Act: -0.1700

Data Index: 7625345 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0680. Min Act: -0.1700

Data Index: 1753000 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0499. Min Act: -0.1700

Data Index: 7619576 (Open Web Text)

Max Activating Token Index: 564

Text #3

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0203. Min Act: -0.1700

Data Index: 3357776 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0259. Min Act: -0.1700

Data Index: 3074843 (Open Web Text)

Max Activating Token Index: 504

Text #5

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0319. Min Act: -0.1700

Data Index: 2432033 (Open Web Text)

Max Activating Token Index: 437

Text #6

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0136. Min Act: -0.1700

Data Index: 1989645 (Open Web Text)

Max Activating Token Index: 860

Text #7

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9979. Min Act: -0.1700

Data Index: 5641452 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9896. Min Act: -0.1700

Data Index: 5196141 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0061. Min Act: -0.1700

Data Index: 1492214 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0055. Min Act: -0.1700

Data Index: 6424890 (Open Web Text)

Max Activating Token Index: 806

Text #11

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0072. Min Act: -0.1700

Data Index: 6347663 (Open Web Text)

Max Activating Token Index: 875

Text #12

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9822. Min Act: -0.1700

Data Index: 1145046 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0107. Min Act: -0.1700

Data Index: 860112 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 4.1041. Min Range: -4.1041

Max Act: 4.0100. Min Act: -0.1700

Data Index: 668881 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9536. Min Act: -0.1700

Data Index: 4949322 (Open Web Text)

Max Activating Token Index: 1000

Text #16

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9698. Min Act: -0.1700

Data Index: 5404371 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9594. Min Act: -0.1700

Data Index: 5741843 (Open Web Text)

Max Activating Token Index: 431

Text #18

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9708. Min Act: -0.1700

Data Index: 1810130 (Open Web Text)

Max Activating Token Index: 585

Text #19

Max Range: 4.1041. Min Range: -4.1041

Max Act: 3.9720. Min Act: -0.1700

Data Index: 3649856 (Open Web Text)

Max Activating Token Index: 515