Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1548 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.9779. Min Act: -0.1700
Data Index: 2891876 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8842. Min Act: -0.1700
Data Index: 7643569 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8842. Min Act: -0.1700
Data Index: 8009156 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8842. Min Act: -0.1700
Data Index: 5249018 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8529. Min Act: -0.1700
Data Index: 8403633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8217. Min Act: -0.1700
Data Index: 2586255 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8529. Min Act: -0.1700
Data Index: 588835 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8529. Min Act: -0.1700
Data Index: 720636 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8529. Min Act: -0.1700
Data Index: 2691388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8217. Min Act: -0.1700
Data Index: 5561806 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8217. Min Act: -0.1700
Data Index: 3855664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7904. Min Act: -0.1700
Data Index: 4351821 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.8217. Min Act: -0.1700
Data Index: 4883854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7904. Min Act: -0.1700
Data Index: 3539973 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7904. Min Act: -0.1700
Data Index: 5403886 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7904. Min Act: -0.1700
Data Index: 3986178 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7592. Min Act: -0.1700
Data Index: 5147044 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7592. Min Act: -0.1700
Data Index: 4881019 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7279. Min Act: -0.1700
Data Index: 7093352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9779. Min Range: -4.9779
Max Act: 4.7279. Min Act: -0.1700
Data Index: 796543 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19