Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2204 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.7739. Min Act: -0.1700
Data Index: 3272388 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.7426. Min Act: -0.1700
Data Index: 5358496 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.7426. Min Act: -0.1700
Data Index: 8799044 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.7114. Min Act: -0.1700
Data Index: 5576894 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.6801. Min Act: -0.1700
Data Index: 6046791 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.7114. Min Act: -0.1700
Data Index: 6790175 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.6801. Min Act: -0.1700
Data Index: 4873267 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.6176. Min Act: -0.1700
Data Index: 7618590 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.6176. Min Act: -0.1700
Data Index: 5620134 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.5864. Min Act: -0.1700
Data Index: 6363313 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.5551. Min Act: -0.1700
Data Index: 5924044 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.5239. Min Act: -0.1700
Data Index: 2115471 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.5551. Min Act: -0.1700
Data Index: 5539205 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.4926. Min Act: -0.1700
Data Index: 5940486 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.4926. Min Act: -0.1700
Data Index: 2938123 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.4926. Min Act: -0.1700
Data Index: 5611110 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.3989. Min Act: -0.1700
Data Index: 7658872 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.4301. Min Act: -0.1700
Data Index: 7132033 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.3989. Min Act: -0.1700
Data Index: 6703963 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7739. Min Range: -6.7739
Max Act: 6.4301. Min Act: -0.1700
Data Index: 7007908 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19