Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.1811. Min Act: -0.1700
Data Index: 7095869 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.1499. Min Act: -0.1700
Data Index: 3875853 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.0874. Min Act: -0.1700
Data Index: 6089120 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.0874. Min Act: -0.1700
Data Index: 1282461 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.0561. Min Act: -0.1700
Data Index: 2613487 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 1950425 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 4180981 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 4516946 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 5187756 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8686. Min Act: -0.1700
Data Index: 1787908 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8686. Min Act: -0.1700
Data Index: 7203316 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8061. Min Act: -0.1700
Data Index: 2613483 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.7436. Min Act: -0.1700
Data Index: 5187755 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.7436. Min Act: -0.1700
Data Index: 6918473 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.7124. Min Act: -0.1700
Data Index: 5387361 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.7124. Min Act: -0.1700
Data Index: 3604896 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.7124. Min Act: -0.1700
Data Index: 619376 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.7436. Min Act: -0.1700
Data Index: 7820973 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.6811. Min Act: -0.1700
Data Index: 1156581 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.6811. Min Act: -0.1700
Data Index: 5665482 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19