Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0294. Min Range: -6.0294
Max Act: 6.0294. Min Act: -0.1700
Data Index: 8367732 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0294. Min Range: -6.0294
Max Act: 6.0294. Min Act: -0.1700
Data Index: 607546 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.9044. Min Act: -0.1700
Data Index: 3174138 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.8419. Min Act: -0.1700
Data Index: 3967388 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.8419. Min Act: -0.1700
Data Index: 3205303 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.8107. Min Act: -0.1700
Data Index: 43299 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.8107. Min Act: -0.1700
Data Index: 8103623 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.8107. Min Act: -0.1700
Data Index: 7790221 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7794. Min Act: -0.1700
Data Index: 1358495 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.8107. Min Act: -0.1699
Data Index: 5702874 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7482. Min Act: -0.1700
Data Index: 3784672 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7482. Min Act: -0.1700
Data Index: 533089 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7482. Min Act: -0.1700
Data Index: 5696230 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7482. Min Act: -0.1700
Data Index: 3238482 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7482. Min Act: -0.1700
Data Index: 5784867 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7169. Min Act: -0.1698
Data Index: 1725067 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7169. Min Act: -0.1700
Data Index: 1709293 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7169. Min Act: -0.1700
Data Index: 5968329 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7169. Min Act: -0.1700
Data Index: 2800631 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0294. Min Range: -6.0294
Max Act: 5.7169. Min Act: -0.1700
Data Index: 1796769 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19