Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.7955. Min Act: -0.1700
Data Index: 4623905 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.6705. Min Act: -0.1700
Data Index: 4312461 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.6705. Min Act: -0.1700
Data Index: 1026881 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.5767. Min Act: -0.1700
Data Index: 4970103 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.5767. Min Act: -0.1700
Data Index: 3225512 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.5767. Min Act: -0.1700
Data Index: 2273049 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.5455. Min Act: -0.1700
Data Index: 4663216 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.5455. Min Act: -0.1700
Data Index: 6606392 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4830. Min Act: -0.1700
Data Index: 7675508 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4830. Min Act: -0.1700
Data Index: 1739550 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4830. Min Act: -0.1700
Data Index: 6733879 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.5142. Min Act: -0.1700
Data Index: 5936355 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4517. Min Act: -0.1700
Data Index: 8306666 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4517. Min Act: -0.1700
Data Index: 8011719 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4205. Min Act: -0.1700
Data Index: 5673760 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4517. Min Act: -0.1700
Data Index: 1320806 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.3892. Min Act: -0.1700
Data Index: 128791 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4205. Min Act: -0.1700
Data Index: 814877 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4205. Min Act: -0.1700
Data Index: 841685 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7955. Min Range: -4.7955
Max Act: 4.4205. Min Act: -0.1700
Data Index: 4209295 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19