Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4637. Min Range: -9.4637
Max Act: 9.4637. Min Act: -0.1700
Data Index: 2204166 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4637. Min Range: -9.4637
Max Act: 9.3387. Min Act: -0.1700
Data Index: 84509 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4637. Min Range: -9.4637
Max Act: 9.2762. Min Act: -0.1700
Data Index: 4996136 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4637. Min Range: -9.4637
Max Act: 9.1512. Min Act: -0.1700
Data Index: 2076764 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4637. Min Range: -9.4637
Max Act: 9.0887. Min Act: -0.1700
Data Index: 4732387 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4637. Min Range: -9.4637
Max Act: 9.0262. Min Act: -0.1700
Data Index: 3277693 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 8168334 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.9012. Min Act: -0.1700
Data Index: 8245019 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.9012. Min Act: -0.1700
Data Index: 8821902 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 6825521 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.9012. Min Act: -0.1700
Data Index: 6907055 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 544268 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 7986620 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 7887564 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 512475 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 1190481 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 5552368 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 8308470 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.7762. Min Act: -0.1700
Data Index: 6164660 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4637. Min Range: -9.4637
Max Act: 8.8387. Min Act: -0.1700
Data Index: 8017686 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19