Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4375 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.1634. Min Act: -0.1700
Data Index: 7013434 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0696. Min Act: -0.1700
Data Index: 6827324 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.1009. Min Act: -0.1700
Data Index: 5258994 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0696. Min Act: -0.1700
Data Index: 4316703 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0384. Min Act: -0.1700
Data Index: 2586507 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0384. Min Act: -0.1700
Data Index: 2436341 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0384. Min Act: -0.1698
Data Index: 4101200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0384. Min Act: -0.1700
Data Index: 5748670 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0384. Min Act: -0.1700
Data Index: 1992012 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9759. Min Act: -0.1700
Data Index: 6932884 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0071. Min Act: -0.1700
Data Index: 6526848 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0071. Min Act: -0.1700
Data Index: 6175087 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9759. Min Act: -0.1700
Data Index: 5251718 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1634. Min Range: -5.1634
Max Act: 5.0071. Min Act: -0.1700
Data Index: 6262749 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9759. Min Act: -0.1700
Data Index: 744143 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9759. Min Act: -0.1700
Data Index: 4399909 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9759. Min Act: -0.1700
Data Index: 1385788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9446. Min Act: -0.1700
Data Index: 1214913 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9446. Min Act: -0.1700
Data Index: 4416434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1634. Min Range: -5.1634
Max Act: 4.9446. Min Act: -0.1700
Data Index: 62857 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19