Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.2529. Min Act: -0.1700
Data Index: 7459993 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.0966. Min Act: -0.1700
Data Index: 2670103 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.0966. Min Act: -0.1700
Data Index: 459491 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.0654. Min Act: -0.1700
Data Index: 4394332 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.0654. Min Act: -0.1700
Data Index: 7614114 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.0341. Min Act: -0.1700
Data Index: 2072960 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.0654. Min Act: -0.1700
Data Index: 1442999 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2529. Min Range: -7.2529
Max Act: 7.0029. Min Act: -0.1700
Data Index: 5262491 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9716. Min Act: -0.1700
Data Index: 4676059 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9716. Min Act: -0.1700
Data Index: 8314349 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9716. Min Act: -0.1700
Data Index: 204848 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9404. Min Act: -0.1700
Data Index: 1377660 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9404. Min Act: -0.1700
Data Index: 6384819 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9404. Min Act: -0.1700
Data Index: 744949 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9404. Min Act: -0.1700
Data Index: 5446112 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9404. Min Act: -0.1700
Data Index: 6946090 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9091. Min Act: -0.1700
Data Index: 3937347 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.9091. Min Act: -0.1700
Data Index: 1229840 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.8779. Min Act: -0.1700
Data Index: 3514865 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2529. Min Range: -7.2529
Max Act: 6.8779. Min Act: -0.1700
Data Index: 4290137 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19