Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5346 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.3668. Min Act: -0.1700
Data Index: 233109 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.3198. Min Act: -0.1700
Data Index: 6480445 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1784. Min Act: -0.1700
Data Index: 6644483 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1784. Min Act: -0.1700
Data Index: 4434687 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.1784. Min Act: -0.1700
Data Index: 1283201 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0681. Min Act: -0.1700
Data Index: 6219514 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0839. Min Act: -0.1700
Data Index: 6743439 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0523. Min Act: -0.1700
Data Index: 2469120 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0681. Min Act: -0.1700
Data Index: 5742385 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0365. Min Act: -0.1700
Data Index: 8384595 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0365. Min Act: -0.1700
Data Index: 5166993 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0365. Min Act: -0.1700
Data Index: 5146230 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0049. Min Act: -0.1700
Data Index: 7072742 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0049. Min Act: -0.1700
Data Index: 5374249 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0049. Min Act: -0.1700
Data Index: 5012813 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3668. Min Range: -3.3668
Max Act: 2.9733. Min Act: -0.1700
Data Index: 3952640 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3668. Min Range: -3.3668
Max Act: 3.0049. Min Act: -0.1700
Data Index: 5878643 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3668. Min Range: -3.3668
Max Act: 2.9891. Min Act: -0.1700
Data Index: 3653787 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3668. Min Range: -3.3668
Max Act: 2.9891. Min Act: -0.1700
Data Index: 4943052 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3668. Min Range: -3.3668
Max Act: 2.9733. Min Act: -0.1700
Data Index: 5332543 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19