Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4675 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.4591. Min Act: -0.1700
Data Index: 3278006 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3654. Min Act: -0.1700
Data Index: 6398829 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3654. Min Act: -0.1700
Data Index: 8421773 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3341. Min Act: -0.1700
Data Index: 7070421 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3341. Min Act: -0.1700
Data Index: 4574855 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3341. Min Act: -0.1700
Data Index: 3678643 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2716. Min Act: -0.1700
Data Index: 5797511 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3341. Min Act: -0.1700
Data Index: 5744304 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3029. Min Act: -0.1700
Data Index: 8692980 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2716. Min Act: -0.1700
Data Index: 1058270 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.3029. Min Act: -0.1700
Data Index: 4252348 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2404. Min Act: -0.1700
Data Index: 7340517 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2404. Min Act: -0.1700
Data Index: 4866870 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2404. Min Act: -0.1700
Data Index: 1752804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2404. Min Act: -0.1700
Data Index: 6861707 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2404. Min Act: -0.1700
Data Index: 121812 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.1778. Min Act: -0.1700
Data Index: 5650976 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.2091. Min Act: -0.1700
Data Index: 2232427 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.1778. Min Act: -0.1700
Data Index: 4217472 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4591. Min Range: -4.4591
Max Act: 4.1466. Min Act: -0.1700
Data Index: 8374715 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19