Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1702 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.9384. Min Act: -0.1700
Data Index: 5459824 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.9384. Min Act: -0.1700
Data Index: 4077006 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.9384. Min Act: -0.1700
Data Index: 3465451 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.9072. Min Act: -0.1700
Data Index: 2603581 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8759. Min Act: -0.1700
Data Index: 575668 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8759. Min Act: -0.1700
Data Index: 6973707 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8759. Min Act: -0.1700
Data Index: 2188978 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8447. Min Act: -0.1700
Data Index: 7316433 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8134. Min Act: -0.1700
Data Index: 5585317 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8134. Min Act: -0.1700
Data Index: 2889581 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8134. Min Act: -0.1700
Data Index: 4460483 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.8134. Min Act: -0.1700
Data Index: 2025182 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7822. Min Act: -0.1700
Data Index: 7004136 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7509. Min Act: -0.1700
Data Index: 6700502 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7822. Min Act: -0.1700
Data Index: 1323024 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7822. Min Act: -0.1700
Data Index: 449002 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7822. Min Act: -0.1700
Data Index: 6694781 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7509. Min Act: -0.1700
Data Index: 6230065 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7197. Min Act: -0.1700
Data Index: 5337250 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9384. Min Range: -5.9384
Max Act: 5.7197. Min Act: -0.1700
Data Index: 6409897 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19