Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4263 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3720. Min Range: -8.3720
Max Act: 8.3720. Min Act: -0.1700
Data Index: 282866 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3720. Min Range: -8.3720
Max Act: 8.1220. Min Act: -0.1700
Data Index: 8045999 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.9970. Min Act: -0.1700
Data Index: 5613341 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.9970. Min Act: -0.1700
Data Index: 5113812 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.8095. Min Act: -0.1700
Data Index: 315556 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.8095. Min Act: -0.1700
Data Index: 4206696 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.8095. Min Act: -0.1700
Data Index: 4945814 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.7470. Min Act: -0.1700
Data Index: 8686378 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.6845. Min Act: -0.1700
Data Index: 5826294 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.6845. Min Act: -0.1700
Data Index: 1856670 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.6845. Min Act: -0.1700
Data Index: 8139287 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.6220. Min Act: -0.1700
Data Index: 221564 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.6220. Min Act: -0.1700
Data Index: 637094 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.6220. Min Act: -0.1700
Data Index: 7608608 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.6220. Min Act: -0.1700
Data Index: 7317423 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.5595. Min Act: -0.1700
Data Index: 441124 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.5595. Min Act: -0.1700
Data Index: 2781725 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.5595. Min Act: -0.1700
Data Index: 747663 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.5282. Min Act: -0.1700
Data Index: 2789118 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3720. Min Range: -8.3720
Max Act: 7.5282. Min Act: -0.1700
Data Index: 2076193 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19