Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.6571. Min Act: -0.1700
Data Index: 4136386 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.6258. Min Act: -0.1700
Data Index: 4209769 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5789. Min Act: -0.1700
Data Index: 2248230 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5475. Min Act: -0.1700
Data Index: 704351 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5475. Min Act: -0.1700
Data Index: 1352470 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5319. Min Act: -0.1700
Data Index: 4666485 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5162. Min Act: -0.1700
Data Index: 1527217 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5006. Min Act: -0.1700
Data Index: 1337289 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.5006. Min Act: -0.1700
Data Index: 1995688 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4849. Min Act: -0.1700
Data Index: 8227232 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4692. Min Act: -0.1700
Data Index: 4397879 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4692. Min Act: -0.1700
Data Index: 4019448 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4536. Min Act: -0.1700
Data Index: 5965959 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4692. Min Act: -0.1700
Data Index: 3105239 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4379. Min Act: -0.1700
Data Index: 3442280 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4536. Min Act: -0.1700
Data Index: 5554653 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4222. Min Act: -0.1700
Data Index: 2518113 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4222. Min Act: -0.1700
Data Index: 3923333 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4379. Min Act: -0.1700
Data Index: 4649355 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6571. Min Range: -3.6571
Max Act: 3.4222. Min Act: -0.1700
Data Index: 7959930 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19