Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.7012. Min Act: -0.1700
Data Index: 7543735 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.5137. Min Act: -0.1700
Data Index: 6214054 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.5762. Min Act: -0.1700
Data Index: 7563516 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.5762. Min Act: -0.1700
Data Index: 4225221 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.5762. Min Act: -0.1700
Data Index: 7813838 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.5137. Min Act: -0.1700
Data Index: 5908415 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.4512. Min Act: -0.1700
Data Index: 8223861 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.4512. Min Act: -0.1700
Data Index: 444184 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.4512. Min Act: -0.1700
Data Index: 4845999 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.4512. Min Act: -0.1700
Data Index: 6172990 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.4512. Min Act: -0.1700
Data Index: 41041 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.3887. Min Act: -0.1700
Data Index: 5627249 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.3887. Min Act: -0.1700
Data Index: 4421690 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.4512. Min Act: -0.1700
Data Index: 3730159 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.3262. Min Act: -0.1700
Data Index: 1936728 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.5137. Min Act: -0.1700
Data Index: 8033941 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.3262. Min Act: -0.1700
Data Index: 8471872 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.3262. Min Act: -0.1700
Data Index: 347065 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.2637. Min Act: -0.1700
Data Index: 5953206 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7012. Min Range: -8.7012
Max Act: 8.2637. Min Act: -0.1700
Data Index: 2784704 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19