Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4218 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9604. Min Act: -0.1700
Data Index: 2178437 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9434. Min Act: -0.1700
Data Index: 4404961 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9434. Min Act: -0.1700
Data Index: 5660164 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9434. Min Act: -0.1700
Data Index: 2993007 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9264. Min Act: -0.1700
Data Index: 7790643 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.9094. Min Act: -0.1700
Data Index: 1748041 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8923. Min Act: -0.1700
Data Index: 965921 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8923. Min Act: -0.1700
Data Index: 8777063 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8753. Min Act: -0.1700
Data Index: 4141964 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8410. Min Act: -0.1700
Data Index: 2916884 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8239. Min Act: -0.1700
Data Index: 2511080 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8239. Min Act: -0.1700
Data Index: 5250108 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8239. Min Act: -0.1700
Data Index: 2953099 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8067. Min Act: -0.1700
Data Index: 5652503 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8067. Min Act: -0.1700
Data Index: 6395591 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.8067. Min Act: -0.1700
Data Index: 4164412 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7895. Min Act: -0.1700
Data Index: 7252647 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7895. Min Act: -0.1700
Data Index: 1419772 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7722. Min Act: -0.1700
Data Index: 1617508 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9604. Min Range: -1.9604
Max Act: 1.7895. Min Act: -0.1700
Data Index: 4335735 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19