Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 894 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.6667. Min Act: -0.1700
Data Index: 5803810 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.6667. Min Act: -0.1700
Data Index: 6059008 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.6667. Min Act: -0.1700
Data Index: 7248495 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.6354. Min Act: -0.1700
Data Index: 5964592 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.6354. Min Act: -0.1700
Data Index: 7687129 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5729. Min Act: -0.1700
Data Index: 2908532 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.6354. Min Act: -0.1700
Data Index: 8427664 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5729. Min Act: -0.1700
Data Index: 1843845 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5729. Min Act: -0.1700
Data Index: 7690407 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5417. Min Act: -0.1700
Data Index: 2401484 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5729. Min Act: -0.1700
Data Index: 7460886 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5417. Min Act: -0.1700
Data Index: 2573777 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5104. Min Act: -0.1700
Data Index: 3609409 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5104. Min Act: -0.1700
Data Index: 7315688 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5104. Min Act: -0.1700
Data Index: 538592 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5104. Min Act: -0.1700
Data Index: 5388511 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5417. Min Act: -0.1700
Data Index: 5582199 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.5104. Min Act: -0.1700
Data Index: 1710600 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.4792. Min Act: -0.1700
Data Index: 5473736 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6667. Min Range: -4.6667
Max Act: 4.4792. Min Act: -0.1700
Data Index: 4025699 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19