Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.5462. Min Act: -0.1700
Data Index: 1022143 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.4837. Min Act: -0.1700
Data Index: 4100228 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.4212. Min Act: -0.1700
Data Index: 1703835 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.2650. Min Act: -0.1700
Data Index: 7597457 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.2337. Min Act: -0.1700
Data Index: 7363421 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.2025. Min Act: -0.1700
Data Index: 6846547 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.0775. Min Act: -0.1700
Data Index: 7573168 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.1087. Min Act: -0.1700
Data Index: 6366249 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.1087. Min Act: -0.1700
Data Index: 5548846 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.1087. Min Act: -0.1700
Data Index: 7756568 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.1400. Min Act: -0.1700
Data Index: 5044845 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.1087. Min Act: -0.1700
Data Index: 4436925 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.0462. Min Act: -0.1700
Data Index: 7521467 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.0462. Min Act: -0.1700
Data Index: 3744272 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.0462. Min Act: -0.1700
Data Index: 6378878 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.0150. Min Act: -0.1700
Data Index: 4057325 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5462. Min Range: -7.5462
Max Act: 7.0150. Min Act: -0.1700
Data Index: 6232634 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5462. Min Range: -7.5462
Max Act: 6.9837. Min Act: -0.1700
Data Index: 8223481 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5462. Min Range: -7.5462
Max Act: 6.9837. Min Act: -0.1700
Data Index: 8311717 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5462. Min Range: -7.5462
Max Act: 6.9837. Min Act: -0.1700
Data Index: 7550619 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19