Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3672. Min Range: -11.3672
Max Act: 11.3672. Min Act: -0.1700
Data Index: 100933 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3672. Min Range: -11.3672
Max Act: 11.1797. Min Act: -0.1700
Data Index: 7841491 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3672. Min Range: -11.3672
Max Act: 10.5547. Min Act: -0.1700
Data Index: 7307796 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.8672. Min Act: -0.1700
Data Index: 7600509 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.4922. Min Act: -0.1700
Data Index: 897782 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.3047. Min Act: -0.1700
Data Index: 7388596 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.2422. Min Act: -0.1700
Data Index: 21887 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.2422. Min Act: -0.1700
Data Index: 5832017 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.2422. Min Act: -0.1700
Data Index: 5407897 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.1797. Min Act: -0.1700
Data Index: 6273192 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3672. Min Range: -11.3672
Max Act: 9.0547. Min Act: -0.1700
Data Index: 2708211 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.9297. Min Act: -0.1700
Data Index: 1399982 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 2384317 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.8672. Min Act: -0.1700
Data Index: 6588989 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 5820827 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 3083033 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 2471836 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 4123532 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.8047. Min Act: -0.1700
Data Index: 2080725 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3672. Min Range: -11.3672
Max Act: 8.7422. Min Act: -0.1700
Data Index: 5820812 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19