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

Dataset: Open Web Text

Neuron 2969 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: 1.6041. Min Range: -1.6041

Max Act: 1.6041. Min Act: -0.1684

Data Index: 8324588 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.6029. Min Act: -0.1684

Data Index: 2014887 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5914. Min Act: -0.1684

Data Index: 6945517 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5825. Min Act: -0.1684

Data Index: 386150 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5725. Min Act: -0.1684

Data Index: 7602640 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5751. Min Act: -0.1684

Data Index: 4514132 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5572. Min Act: -0.1684

Data Index: 43608 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5502. Min Act: -0.1684

Data Index: 4701559 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5460. Min Act: -0.1684

Data Index: 1803354 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5453. Min Act: -0.1688

Data Index: 5228348 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5378. Min Act: -0.1684

Data Index: 5776407 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5418. Min Act: -0.1684

Data Index: 7585582 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5373. Min Act: -0.1684

Data Index: 5042423 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5262. Min Act: -0.1684

Data Index: 5254544 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5255. Min Act: -0.1700

Data Index: 4377126 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5240. Min Act: -0.1684

Data Index: 4912214 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5269. Min Act: -0.1684

Data Index: 4209380 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5306. Min Act: -0.1684

Data Index: 6389132 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5282. Min Act: -0.1684

Data Index: 4315013 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5307. Min Act: -0.1684

Data Index: 4338840 (Open Web Text)

Max Activating Token Index: 4