Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.9265. Min Act: -0.1700
Data Index: 2751658 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.9265. Min Act: -0.1700
Data Index: 4656230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8952. Min Act: -0.1700
Data Index: 1233256 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8952. Min Act: -0.1700
Data Index: 5298805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8640. Min Act: -0.1700
Data Index: 1544817 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8640. Min Act: -0.1700
Data Index: 1166025 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8640. Min Act: -0.1700
Data Index: 5414910 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8640. Min Act: -0.1700
Data Index: 1681815 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 4257847 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 2803308 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 1166019 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 556423 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 6979437 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 8718822 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 3236575 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 2173304 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8327. Min Act: -0.1700
Data Index: 1431467 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8014. Min Act: -0.1700
Data Index: 3304078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8014. Min Act: -0.1700
Data Index: 3607284 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9265. Min Range: -3.9265
Max Act: 3.8014. Min Act: -0.1700
Data Index: 4035405 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19