Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0701. Min Range: -5.0701
Max Act: 5.0701. Min Act: -0.1700
Data Index: 7284774 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0701. Min Range: -5.0701
Max Act: 5.0076. Min Act: -0.1700
Data Index: 8323261 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0701. Min Range: -5.0701
Max Act: 5.0076. Min Act: -0.1700
Data Index: 1822559 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.9139. Min Act: -0.1700
Data Index: 2552012 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.9139. Min Act: -0.1700
Data Index: 8387841 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.9139. Min Act: -0.1700
Data Index: 1024100 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.8826. Min Act: -0.1700
Data Index: 711113 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.8826. Min Act: -0.1700
Data Index: 3210223 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.9139. Min Act: -0.1700
Data Index: 655067 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.8201. Min Act: -0.1700
Data Index: 5181663 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.8514. Min Act: -0.1700
Data Index: 2002909 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.8201. Min Act: -0.1700
Data Index: 787976 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.8201. Min Act: -0.1700
Data Index: 2801012 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.7576. Min Act: -0.1700
Data Index: 5602060 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.7264. Min Act: -0.1700
Data Index: 6193519 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.7576. Min Act: -0.1700
Data Index: 2846561 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.7576. Min Act: -0.1700
Data Index: 8515367 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.7576. Min Act: -0.1700
Data Index: 4437930 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.7264. Min Act: -0.1700
Data Index: 5896265 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0701. Min Range: -5.0701
Max Act: 4.6951. Min Act: -0.1700
Data Index: 3144401 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19