Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1773 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.9217. Min Act: -0.1700
Data Index: 7050726 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.7029. Min Act: -0.1700
Data Index: 1958702 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.5779. Min Act: -0.1700
Data Index: 1958703 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.5467. Min Act: -0.1700
Data Index: 2327124 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.4842. Min Act: -0.1700
Data Index: 3519574 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.4842. Min Act: -0.1700
Data Index: 7286684 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.4842. Min Act: -0.1700
Data Index: 2376423 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3904. Min Act: -0.1700
Data Index: 7573987 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3904. Min Act: -0.1700
Data Index: 1997808 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3904. Min Act: -0.1700
Data Index: 3980003 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3904. Min Act: -0.1700
Data Index: 5633994 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3904. Min Act: -0.1700
Data Index: 1089720 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3592. Min Act: -0.1700
Data Index: 1702031 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3592. Min Act: -0.1700
Data Index: 464360 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3592. Min Act: -0.1700
Data Index: 1997806 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3279. Min Act: -0.1700
Data Index: 3133812 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.3279. Min Act: -0.1700
Data Index: 1997807 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.2967. Min Act: -0.1700
Data Index: 4190333 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.2967. Min Act: -0.1700
Data Index: 3691405 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9217. Min Range: -4.9217
Max Act: 4.2967. Min Act: -0.1700
Data Index: 5870626 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19