Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1235 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.5173. Min Act: -0.1699
Data Index: 8547809 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.3923. Min Act: -0.1700
Data Index: 3895575 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.3298. Min Act: -0.1700
Data Index: 6153709 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.3298. Min Act: -0.1700
Data Index: 5091126 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.2986. Min Act: -0.1700
Data Index: 1023502 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.2361. Min Act: -0.1700
Data Index: 1229779 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.2048. Min Act: -0.1700
Data Index: 2132767 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.2361. Min Act: -0.1700
Data Index: 1348850 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.2048. Min Act: -0.1700
Data Index: 5619843 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1736. Min Act: -0.1700
Data Index: 7684258 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1736. Min Act: -0.1700
Data Index: 3458900 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1423. Min Act: -0.1700
Data Index: 4674617 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1736. Min Act: -0.1700
Data Index: 42269 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.0798. Min Act: -0.1700
Data Index: 2302159 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1423. Min Act: -0.1700
Data Index: 3388863 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1423. Min Act: -0.1700
Data Index: 576523 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1736. Min Act: -0.1700
Data Index: 8339278 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1111. Min Act: -0.1700
Data Index: 2032247 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1736. Min Act: -0.1700
Data Index: 4842316 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5173. Min Range: -6.5173
Max Act: 6.1111. Min Act: -0.1700
Data Index: 4456942 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19