Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.6644. Min Act: -0.1700
Data Index: 597137 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.6331. Min Act: -0.1700
Data Index: 7827241 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.6019. Min Act: -0.1700
Data Index: 5962999 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.6019. Min Act: -0.1700
Data Index: 8671993 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.5706. Min Act: -0.1700
Data Index: 688468 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.5394. Min Act: -0.1700
Data Index: 8413568 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.5706. Min Act: -0.1700
Data Index: 1941729 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.5081. Min Act: -0.1700
Data Index: 4321425 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.5081. Min Act: -0.1700
Data Index: 1138656 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4769. Min Act: -0.1700
Data Index: 3349598 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4769. Min Act: -0.1700
Data Index: 1456082 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4769. Min Act: -0.1700
Data Index: 6171212 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4456. Min Act: -0.1700
Data Index: 7022342 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4769. Min Act: -0.1700
Data Index: 7532538 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4456. Min Act: -0.1700
Data Index: 7786416 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4456. Min Act: -0.1700
Data Index: 1775827 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4456. Min Act: -0.1700
Data Index: 2607941 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4456. Min Act: -0.1700
Data Index: 5416956 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4456. Min Act: -0.1700
Data Index: 389894 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6644. Min Range: -4.6644
Max Act: 4.4456. Min Act: -0.1700
Data Index: 2551465 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19