Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.9797. Min Act: -0.1700
Data Index: 69997 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.8860. Min Act: -0.1700
Data Index: 3977598 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.8235. Min Act: -0.1700
Data Index: 5714421 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.7922. Min Act: -0.1700
Data Index: 3080333 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.7297. Min Act: -0.1700
Data Index: 8498012 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.7297. Min Act: -0.1700
Data Index: 6036168 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.6672. Min Act: -0.1700
Data Index: 2872987 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.6360. Min Act: -0.1700
Data Index: 8712233 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.6360. Min Act: -0.1700
Data Index: 8685236 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.6047. Min Act: -0.1700
Data Index: 8451015 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5735. Min Act: -0.1700
Data Index: 2928858 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5735. Min Act: -0.1700
Data Index: 5464445 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5735. Min Act: -0.1700
Data Index: 2857170 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5735. Min Act: -0.1700
Data Index: 6132014 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5422. Min Act: -0.1700
Data Index: 6928634 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5422. Min Act: -0.1700
Data Index: 7267407 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5735. Min Act: -0.1700
Data Index: 5779165 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5422. Min Act: -0.1700
Data Index: 8414753 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.5422. Min Act: -0.1700
Data Index: 2320306 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9797. Min Range: -6.9797
Max Act: 6.4797. Min Act: -0.1700
Data Index: 3919627 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19