Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3715 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.9032. Min Act: -0.1700
Data Index: 3005178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.8720. Min Act: -0.1700
Data Index: 5347601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.8720. Min Act: -0.1699
Data Index: 6513850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.8407. Min Act: -0.1700
Data Index: 2078372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.8095. Min Act: -0.1700
Data Index: 4567358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.8095. Min Act: -0.1700
Data Index: 3013006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.8095. Min Act: -0.1699
Data Index: 7193427 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.8095. Min Act: -0.1700
Data Index: 6836580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1695
Data Index: 5126072 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1700
Data Index: 1228397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1700
Data Index: 8120352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1700
Data Index: 885850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1700
Data Index: 3150248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7470. Min Act: -0.1700
Data Index: 189813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1700
Data Index: 5842103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7470. Min Act: -0.1700
Data Index: 362629 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1700
Data Index: 763864 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7782. Min Act: -0.1700
Data Index: 4105589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7470. Min Act: -0.1698
Data Index: 3552244 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9032. Min Range: -4.9032
Max Act: 4.7470. Min Act: -0.1700
Data Index: 3676340 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19