Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.5058. Min Act: -0.1700
Data Index: 7618328 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.4120. Min Act: -0.1700
Data Index: 8754117 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.1933. Min Act: -0.1700
Data Index: 1356910 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.1933. Min Act: -0.1700
Data Index: 503760 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.1933. Min Act: -0.1700
Data Index: 1183529 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.1933. Min Act: -0.1700
Data Index: 5418841 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.1308. Min Act: -0.1700
Data Index: 8782774 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.1308. Min Act: -0.1700
Data Index: 4783048 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0683. Min Act: -0.1700
Data Index: 7121559 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0995. Min Act: -0.1700
Data Index: 855108 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0995. Min Act: -0.1700
Data Index: 3817714 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0683. Min Act: -0.1700
Data Index: 1610039 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0995. Min Act: -0.1700
Data Index: 2401982 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0683. Min Act: -0.1700
Data Index: 2775076 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0995. Min Act: -0.1700
Data Index: 671590 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0683. Min Act: -0.1700
Data Index: 30995 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0995. Min Act: -0.1700
Data Index: 8177023 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0995. Min Act: -0.1700
Data Index: 800157 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0683. Min Act: -0.1700
Data Index: 810709 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5058. Min Range: -5.5058
Max Act: 5.0370. Min Act: -0.1700
Data Index: 5956011 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19