Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2699 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0902. Min Range: -7.0902
Max Act: 7.0902. Min Act: -0.1700
Data Index: 2116360 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.8715. Min Act: -0.1700
Data Index: 5752007 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.7465. Min Act: -0.1700
Data Index: 1491596 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.5902. Min Act: -0.1700
Data Index: 5433292 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.5277. Min Act: -0.1700
Data Index: 5202583 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.5277. Min Act: -0.1700
Data Index: 2488859 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.5590. Min Act: -0.1700
Data Index: 2672793 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.5277. Min Act: -0.1700
Data Index: 473772 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.4340. Min Act: -0.1700
Data Index: 4656067 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.4340. Min Act: -0.1700
Data Index: 5337642 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.4027. Min Act: -0.1700
Data Index: 5716405 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.3715. Min Act: -0.1700
Data Index: 7431184 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.3715. Min Act: -0.1700
Data Index: 2133806 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.3402. Min Act: -0.1700
Data Index: 7819085 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.3402. Min Act: -0.1700
Data Index: 8711969 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.2777. Min Act: -0.1700
Data Index: 6051929 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.3090. Min Act: -0.1700
Data Index: 5264854 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.3090. Min Act: -0.1700
Data Index: 6016088 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.3090. Min Act: -0.1700
Data Index: 2558679 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0902. Min Range: -7.0902
Max Act: 6.2777. Min Act: -0.1700
Data Index: 5812237 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19