Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4584 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.5019. Min Act: -0.1700
Data Index: 5691233 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.2832. Min Act: -0.1700
Data Index: 6998273 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.2207. Min Act: -0.1700
Data Index: 7533713 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.1894. Min Act: -0.1700
Data Index: 2194898 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0957. Min Act: -0.1700
Data Index: 2155726 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0957. Min Act: -0.1700
Data Index: 8368039 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0957. Min Act: -0.1700
Data Index: 8533058 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0644. Min Act: -0.1700
Data Index: 7835378 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0644. Min Act: -0.1700
Data Index: 7942733 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0644. Min Act: -0.1700
Data Index: 1974425 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0332. Min Act: -0.1700
Data Index: 4265010 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0332. Min Act: -0.1700
Data Index: 4604690 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0019. Min Act: -0.1700
Data Index: 6855473 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5019. Min Range: -7.5019
Max Act: 7.0019. Min Act: -0.1700
Data Index: 6893025 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5019. Min Range: -7.5019
Max Act: 6.9707. Min Act: -0.1700
Data Index: 7835384 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5019. Min Range: -7.5019
Max Act: 6.9394. Min Act: -0.1700
Data Index: 5703170 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5019. Min Range: -7.5019
Max Act: 6.9707. Min Act: -0.1700
Data Index: 125142 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5019. Min Range: -7.5019
Max Act: 6.9707. Min Act: -0.1700
Data Index: 5061101 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5019. Min Range: -7.5019
Max Act: 6.9394. Min Act: -0.1700
Data Index: 8209856 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5019. Min Range: -7.5019
Max Act: 6.9707. Min Act: -0.1700
Data Index: 2774721 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19