Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.7753. Min Act: -0.1700
Data Index: 1065910 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.7753. Min Act: -0.1700
Data Index: 1000974 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.6503. Min Act: -0.1700
Data Index: 2749042 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.5878. Min Act: -0.1700
Data Index: 2652388 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.5253. Min Act: -0.1700
Data Index: 6568492 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.4940. Min Act: -0.1700
Data Index: 7256962 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.4628. Min Act: -0.1700
Data Index: 4929950 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.3690. Min Act: -0.1700
Data Index: 4933847 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.3378. Min Act: -0.1700
Data Index: 3427300 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.3378. Min Act: -0.1700
Data Index: 8806242 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.3378. Min Act: -0.1700
Data Index: 5068020 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.2753. Min Act: -0.1700
Data Index: 7574500 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.2753. Min Act: -0.1700
Data Index: 2397799 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.2753. Min Act: -0.1700
Data Index: 4704888 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.2753. Min Act: -0.1700
Data Index: 8332633 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.2128. Min Act: -0.1700
Data Index: 7388953 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.2128. Min Act: -0.1700
Data Index: 7511082 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.1815. Min Act: -0.1700
Data Index: 6771367 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.2128. Min Act: -0.1700
Data Index: 7032750 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7753. Min Range: -7.7753
Max Act: 7.1815. Min Act: -0.1700
Data Index: 3799995 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19