Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4828. Min Act: -0.1700
Data Index: 7879705 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4828. Min Act: -0.1700
Data Index: 3372998 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4828. Min Act: -0.1700
Data Index: 218641 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1787204 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1777267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 163605 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 292242 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1496323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1312913 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1699
Data Index: 2390415 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1298560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1274353 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 263651 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1118713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 498265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 747543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 979807 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 655987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1698
Data Index: 1934664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4828. Min Range: -5.4828
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1811457 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19