Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1110 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.7641. Min Act: -0.1700
Data Index: 7209103 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.7328. Min Act: -0.1700
Data Index: 1227 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.6391. Min Act: -0.1700
Data Index: 1751404 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.5141. Min Act: -0.1700
Data Index: 764507 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.4828. Min Act: -0.1700
Data Index: 5473869 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.4203. Min Act: -0.1700
Data Index: 4624891 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.4203. Min Act: -0.1700
Data Index: 8610029 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.4203. Min Act: -0.1700
Data Index: 2041604 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.3891. Min Act: -0.1700
Data Index: 1812036 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.3266. Min Act: -0.1700
Data Index: 943344 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2953. Min Act: -0.1700
Data Index: 6020683 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.3266. Min Act: -0.1700
Data Index: 5668688 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2953. Min Act: -0.1700
Data Index: 4264435 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2953. Min Act: -0.1700
Data Index: 7161588 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2641. Min Act: -0.1700
Data Index: 2203751 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2641. Min Act: -0.1700
Data Index: 8404414 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2328. Min Act: -0.1700
Data Index: 1558206 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2328. Min Act: -0.1700
Data Index: 550831 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.2016. Min Act: -0.1700
Data Index: 478431 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7641. Min Range: -6.7641
Max Act: 6.1703. Min Act: -0.1700
Data Index: 6368918 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19