Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1861 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1521. Min Range: -8.1521
Max Act: 8.1521. Min Act: -0.1700
Data Index: 4182133 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1521. Min Range: -8.1521
Max Act: 8.0896. Min Act: -0.1700
Data Index: 4441266 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1521. Min Range: -8.1521
Max Act: 8.0271. Min Act: -0.1700
Data Index: 8241168 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1521. Min Range: -8.1521
Max Act: 8.0896. Min Act: -0.1700
Data Index: 1801469 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1521. Min Range: -8.1521
Max Act: 8.0271. Min Act: -0.1700
Data Index: 6606546 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1521. Min Range: -8.1521
Max Act: 8.0271. Min Act: -0.1700
Data Index: 7697286 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.9646. Min Act: -0.1700
Data Index: 4824542 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.9646. Min Act: -0.1700
Data Index: 4574744 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.9021. Min Act: -0.1700
Data Index: 8301274 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.9021. Min Act: -0.1700
Data Index: 52822 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.9021. Min Act: -0.1700
Data Index: 5739193 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.9021. Min Act: -0.1700
Data Index: 596006 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.9021. Min Act: -0.1700
Data Index: 5268690 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.8396. Min Act: -0.1700
Data Index: 5566052 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.8396. Min Act: -0.1700
Data Index: 391892 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.8084. Min Act: -0.1700
Data Index: 2962988 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.8084. Min Act: -0.1700
Data Index: 4005703 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.7771. Min Act: -0.1700
Data Index: 5300360 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.7771. Min Act: -0.1700
Data Index: 5509373 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1521. Min Range: -8.1521
Max Act: 7.7771. Min Act: -0.1700
Data Index: 3273346 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19