Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3171 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1875. Min Range: -6.1875
Max Act: 6.1875. Min Act: -0.1700
Data Index: 178602 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1875. Min Range: -6.1875
Max Act: 6.1250. Min Act: -0.1700
Data Index: 7109219 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1875. Min Range: -6.1875
Max Act: 6.0937. Min Act: -0.1700
Data Index: 5338989 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1875. Min Range: -6.1875
Max Act: 6.0625. Min Act: -0.1700
Data Index: 6106687 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.9687. Min Act: -0.1700
Data Index: 492756 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.9687. Min Act: -0.1700
Data Index: 3441796 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.9687. Min Act: -0.1700
Data Index: 1054893 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.9375. Min Act: -0.1700
Data Index: 6202084 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.8750. Min Act: -0.1700
Data Index: 7028759 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.8125. Min Act: -0.1700
Data Index: 3342870 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.8125. Min Act: -0.1700
Data Index: 3418820 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.8125. Min Act: -0.1700
Data Index: 1773852 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7812. Min Act: -0.1700
Data Index: 982763 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7812. Min Act: -0.1700
Data Index: 3366897 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7812. Min Act: -0.1700
Data Index: 1405559 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7812. Min Act: -0.1700
Data Index: 3298119 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7500. Min Act: -0.1700
Data Index: 3901556 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7187. Min Act: -0.1700
Data Index: 2976482 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7187. Min Act: -0.1700
Data Index: 2641995 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1875. Min Range: -6.1875
Max Act: 5.7187. Min Act: -0.1700
Data Index: 7889846 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19