Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4529 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.7123. Min Act: -0.1700
Data Index: 4177537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6810. Min Act: -0.1700
Data Index: 2165853 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6498. Min Act: -0.1700
Data Index: 1313571 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6498. Min Act: -0.1700
Data Index: 1545937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1700
Data Index: 5255281 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1700
Data Index: 5081018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1700
Data Index: 6855227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1700
Data Index: 1002285 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1700
Data Index: 2282537 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1700
Data Index: 6629688 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1699
Data Index: 5224837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.6185. Min Act: -0.1700
Data Index: 7452718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5872. Min Act: -0.1699
Data Index: 3450642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5872. Min Act: -0.1700
Data Index: 5220880 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5872. Min Act: -0.1700
Data Index: 3099634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5872. Min Act: -0.1700
Data Index: 4551374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5872. Min Act: -0.1700
Data Index: 1066177 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5558. Min Act: -0.1700
Data Index: 2369853 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5872. Min Act: -0.1700
Data Index: 4617159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7123. Min Range: -3.7123
Max Act: 3.5872. Min Act: -0.1700
Data Index: 7404116 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19