Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4444 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 144659 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 114384 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 71148 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 61690 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 161779 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 105263 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 103483 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 334702 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 91852 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 39684 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 167663 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 308382 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 35305 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 304279 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 245744 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 15096 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 229950 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 211430 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 206581 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8783. Min Range: -3.8783
Max Act: 3.8783. Min Act: -0.1700
Data Index: 4821 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19