Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.3000. Min Act: -0.1700
Data Index: 4659908 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.2688. Min Act: -0.1700
Data Index: 2688096 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.2688. Min Act: -0.1700
Data Index: 4597988 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.1750. Min Act: -0.1700
Data Index: 6271242 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.1125. Min Act: -0.1700
Data Index: 7609485 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0813. Min Act: -0.1700
Data Index: 8825648 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0813. Min Act: -0.1700
Data Index: 5947608 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0188. Min Act: -0.1700
Data Index: 7265666 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0188. Min Act: -0.1700
Data Index: 2681645 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0188. Min Act: -0.1700
Data Index: 869204 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0188. Min Act: -0.1700
Data Index: 4848522 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0500. Min Act: -0.1700
Data Index: 8709482 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.0500. Min Act: -0.1700
Data Index: 6314330 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9875. Min Act: -0.1700
Data Index: 7393343 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9875. Min Act: -0.1700
Data Index: 6646198 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9563. Min Act: -0.1700
Data Index: 8815660 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9875. Min Act: -0.1700
Data Index: 3899523 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9563. Min Act: -0.1700
Data Index: 604906 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9563. Min Act: -0.1700
Data Index: 605748 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9563. Min Act: -0.1700
Data Index: 1255006 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19