Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5251 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2981. Min Range: -6.2981
Max Act: 6.2981. Min Act: -0.1700
Data Index: 6717537 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.9544. Min Act: -0.1700
Data Index: 5338333 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.9544. Min Act: -0.1700
Data Index: 2106284 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.9231. Min Act: -0.1700
Data Index: 4255800 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.8919. Min Act: -0.1700
Data Index: 6007804 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.8919. Min Act: -0.1700
Data Index: 7178462 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.8294. Min Act: -0.1700
Data Index: 5849186 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.7981. Min Act: -0.1700
Data Index: 3326114 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.7669. Min Act: -0.1700
Data Index: 803778 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.7044. Min Act: -0.1700
Data Index: 527888 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.6731. Min Act: -0.1700
Data Index: 7210249 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.6419. Min Act: -0.1700
Data Index: 3843838 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.6419. Min Act: -0.1700
Data Index: 472476 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.6106. Min Act: -0.1700
Data Index: 6616980 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.6106. Min Act: -0.1700
Data Index: 1770842 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.6106. Min Act: -0.1700
Data Index: 3856193 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.6106. Min Act: -0.1700
Data Index: 7656482 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.5794. Min Act: -0.1700
Data Index: 1453617 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.5794. Min Act: -0.1700
Data Index: 6854645 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2981. Min Range: -6.2981
Max Act: 5.5794. Min Act: -0.1700
Data Index: 2569957 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19