Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5767. Min Range: -9.5767
Max Act: 9.5767. Min Act: -0.1700
Data Index: 7761030 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5767. Min Range: -9.5767
Max Act: 9.4517. Min Act: -0.1696
Data Index: 5063184 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5767. Min Range: -9.5767
Max Act: 9.2017. Min Act: -0.1700
Data Index: 4461261 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5767. Min Range: -9.5767
Max Act: 9.2017. Min Act: -0.1700
Data Index: 7404728 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5767. Min Range: -9.5767
Max Act: 9.1392. Min Act: -0.1700
Data Index: 5507218 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5767. Min Range: -9.5767
Max Act: 9.0142. Min Act: -0.1700
Data Index: 1626438 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.9517. Min Act: -0.1700
Data Index: 4580487 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.8892. Min Act: -0.1700
Data Index: 5028480 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.8892. Min Act: -0.1700
Data Index: 6398651 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.8892. Min Act: -0.1700
Data Index: 8241307 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.8267. Min Act: -0.1700
Data Index: 2105292 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.8267. Min Act: -0.1700
Data Index: 8163649 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.8267. Min Act: -0.1700
Data Index: 5912818 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.7642. Min Act: -0.1700
Data Index: 6007566 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.7642. Min Act: -0.1700
Data Index: 2492158 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.7642. Min Act: -0.1700
Data Index: 5570715 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.7017. Min Act: -0.1700
Data Index: 6167890 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.7017. Min Act: -0.1700
Data Index: 7846269 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.7017. Min Act: -0.1700
Data Index: 7934365 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5767. Min Range: -9.5767
Max Act: 8.6392. Min Act: -0.1700
Data Index: 7139472 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19