Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1679 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.7747. Min Act: -0.1700
Data Index: 2062885 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.6497. Min Act: -0.1700
Data Index: 1156294 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.6497. Min Act: -0.1700
Data Index: 3253513 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.4622. Min Act: -0.1700
Data Index: 3514844 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.3372. Min Act: -0.1700
Data Index: 4732838 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.2747. Min Act: -0.1700
Data Index: 4005130 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.1497. Min Act: -0.1700
Data Index: 8019356 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.0872. Min Act: -0.1700
Data Index: 7240997 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.9622. Min Act: -0.1700
Data Index: 5694427 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.0247. Min Act: -0.1700
Data Index: 1926037 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.7747. Min Range: -14.7747
Max Act: 14.0247. Min Act: -0.1700
Data Index: 7017314 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.8372. Min Act: -0.1700
Data Index: 7096582 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.8372. Min Act: -0.1700
Data Index: 7112915 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.7747. Min Act: -0.1700
Data Index: 2570106 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.7747. Min Act: -0.1700
Data Index: 1481487 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.7122. Min Act: -0.1700
Data Index: 3933369 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.7122. Min Act: -0.1700
Data Index: 2078963 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.7122. Min Act: -0.1700
Data Index: 7847494 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.7122. Min Act: -0.1700
Data Index: 6990841 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.7747. Min Range: -14.7747
Max Act: 13.6497. Min Act: -0.1700
Data Index: 2503150 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19