Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.7995. Min Act: -0.1700
Data Index: 8553112 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.7676. Min Act: -0.1700
Data Index: 735120 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.7357. Min Act: -0.1700
Data Index: 4738518 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.7037. Min Act: -0.1700
Data Index: 6626252 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.6557. Min Act: -0.1700
Data Index: 4556830 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.6717. Min Act: -0.1700
Data Index: 845170 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.6075. Min Act: -0.1700
Data Index: 5735866 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5914. Min Act: -0.1700
Data Index: 6385232 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5914. Min Act: -0.1700
Data Index: 2896013 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5914. Min Act: -0.1700
Data Index: 2954939 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5753. Min Act: -0.1700
Data Index: 4815853 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5591. Min Act: -0.1700
Data Index: 8627567 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5591. Min Act: -0.1700
Data Index: 6105881 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5591. Min Act: -0.1700
Data Index: 7310939 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5591. Min Act: -0.1700
Data Index: 1166140 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5430. Min Act: -0.1700
Data Index: 3060921 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5430. Min Act: -0.1700
Data Index: 8096898 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5430. Min Act: -0.1700
Data Index: 33321 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5430. Min Act: -0.1700
Data Index: 1069829 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7995. Min Range: -2.7995
Max Act: 2.5430. Min Act: -0.1700
Data Index: 3152901 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19