Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3691 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.9540. Min Act: -0.1700
Data Index: 5268660 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.9540. Min Act: -0.1700
Data Index: 4127702 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.9540. Min Act: -0.1700
Data Index: 5654252 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.8915. Min Act: -0.1700
Data Index: 817859 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.8915. Min Act: -0.1700
Data Index: 4579202 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.8290. Min Act: -0.1700
Data Index: 1704106 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.8290. Min Act: -0.1700
Data Index: 8070008 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.7665. Min Act: -0.1700
Data Index: 8260833 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.7665. Min Act: -0.1700
Data Index: 4031250 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.7040. Min Act: -0.1700
Data Index: 326663 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 7907198 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 2703146 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 1732733 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 3342132 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 3317256 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 910459 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 6813011 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.6415. Min Act: -0.1700
Data Index: 7847099 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.5790. Min Act: -0.1700
Data Index: 701764 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9540. Min Range: -7.9540
Max Act: 7.5790. Min Act: -0.1700
Data Index: 4185786 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19