Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1112. Min Range: -7.1112
Max Act: 7.1112. Min Act: -0.1700
Data Index: 2078632 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.9549. Min Act: -0.1700
Data Index: 5155584 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.9549. Min Act: -0.1700
Data Index: 1578664 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.9237. Min Act: -0.1700
Data Index: 5829955 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.8299. Min Act: -0.1700
Data Index: 257591 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.7362. Min Act: -0.1700
Data Index: 6284925 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.7049. Min Act: -0.1700
Data Index: 3875389 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.7049. Min Act: -0.1700
Data Index: 749990 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.7049. Min Act: -0.1700
Data Index: 5693164 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.6737. Min Act: -0.1700
Data Index: 8186148 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.6737. Min Act: -0.1700
Data Index: 1628160 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.6737. Min Act: -0.1700
Data Index: 6356547 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.7049. Min Act: -0.1700
Data Index: 7871779 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.6424. Min Act: -0.1700
Data Index: 3433943 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.6112. Min Act: -0.1700
Data Index: 2889071 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.6112. Min Act: -0.1700
Data Index: 8796489 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.5799. Min Act: -0.1700
Data Index: 4263516 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.5487. Min Act: -0.1700
Data Index: 5896123 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.5487. Min Act: -0.1700
Data Index: 7336746 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1112. Min Range: -7.1112
Max Act: 6.5174. Min Act: -0.1700
Data Index: 6188509 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19