Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4955 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0913. Min Range: -3.0913
Max Act: 3.0913. Min Act: -0.1700
Data Index: 6613111 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.9966. Min Act: -0.1700
Data Index: 8362903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.9966. Min Act: -0.1700
Data Index: 2794066 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.9333. Min Act: -0.1700
Data Index: 5588683 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.9491. Min Act: -0.1700
Data Index: 3754282 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.9174. Min Act: -0.1700
Data Index: 8076713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.9174. Min Act: -0.1700
Data Index: 1770805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8540. Min Act: -0.1700
Data Index: 2655227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8540. Min Act: -0.1700
Data Index: 6623099 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8540. Min Act: -0.1700
Data Index: 409094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8540. Min Act: -0.1700
Data Index: 8121350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8222. Min Act: -0.1700
Data Index: 6800811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8222. Min Act: -0.1700
Data Index: 1037544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8222. Min Act: -0.1700
Data Index: 8000791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8222. Min Act: -0.1700
Data Index: 1793509 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8222. Min Act: -0.1700
Data Index: 2821783 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.7903. Min Act: -0.1700
Data Index: 7459234 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.7903. Min Act: -0.1700
Data Index: 6483844 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.8063. Min Act: -0.1700
Data Index: 7461900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0913. Min Range: -3.0913
Max Act: 2.7744. Min Act: -0.1700
Data Index: 1347717 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19