Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6256 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.6245. Min Act: -0.1700
Data Index: 406063 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.6245. Min Act: -0.1700
Data Index: 6420973 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.4057. Min Act: -0.1700
Data Index: 401541 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2031978 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.2495. Min Act: -0.1700
Data Index: 3200029 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.2182. Min Act: -0.1700
Data Index: 390071 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1870. Min Act: -0.1700
Data Index: 5399017 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1870. Min Act: -0.1700
Data Index: 6891810 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1870. Min Act: -0.1700
Data Index: 377693 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1870. Min Act: -0.1700
Data Index: 6795890 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1870. Min Act: -0.1700
Data Index: 285512 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1870. Min Act: -0.1700
Data Index: 2032595 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1245. Min Act: -0.1700
Data Index: 3381783 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1245. Min Act: -0.1700
Data Index: 438947 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1245. Min Act: -0.1700
Data Index: 8235453 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1245. Min Act: -0.1700
Data Index: 786131 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.1245. Min Act: -0.1700
Data Index: 243763 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.0932. Min Act: -0.1700
Data Index: 7704752 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.0620. Min Act: -0.1700
Data Index: 848485 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6245. Min Range: -5.6245
Max Act: 5.0620. Min Act: -0.1700
Data Index: 3908100 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19