Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3625. Min Range: -9.3625
Max Act: 9.3625. Min Act: -0.1700
Data Index: 8757506 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3625. Min Range: -9.3625
Max Act: 9.3000. Min Act: -0.1700
Data Index: 7833034 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3625. Min Range: -9.3625
Max Act: 9.1750. Min Act: -0.1700
Data Index: 7932009 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3625. Min Range: -9.3625
Max Act: 9.1750. Min Act: -0.1700
Data Index: 3111179 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.9875. Min Act: -0.1700
Data Index: 1387347 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.9250. Min Act: -0.1700
Data Index: 7832526 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.9250. Min Act: -0.1700
Data Index: 2260972 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.8625. Min Act: -0.1700
Data Index: 6866056 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.8625. Min Act: -0.1700
Data Index: 7137014 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.8625. Min Act: -0.1700
Data Index: 1679405 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.8000. Min Act: -0.1700
Data Index: 3421263 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.7375. Min Act: -0.1700
Data Index: 6476396 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.7375. Min Act: -0.1700
Data Index: 6268792 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.7375. Min Act: -0.1700
Data Index: 6068374 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.8000. Min Act: -0.1700
Data Index: 3202166 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.7375. Min Act: -0.1700
Data Index: 8529203 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.7375. Min Act: -0.1700
Data Index: 1383296 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.6750. Min Act: -0.1700
Data Index: 3849489 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.6750. Min Act: -0.1700
Data Index: 7257097 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3625. Min Range: -9.3625
Max Act: 8.6750. Min Act: -0.1700
Data Index: 3208911 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19