Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 280 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.3516. Min Act: -0.1700
Data Index: 2235642 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.2579. Min Act: -0.1700
Data Index: 5310108 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.2266. Min Act: -0.1700
Data Index: 924513 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 4500370 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.1016. Min Act: -0.1700
Data Index: 3380768 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 7817878 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.1329. Min Act: -0.1700
Data Index: 50789 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.1016. Min Act: -0.1700
Data Index: 4238206 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.0391. Min Act: -0.1700
Data Index: 1149825 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.0704. Min Act: -0.1700
Data Index: 5989919 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.0391. Min Act: -0.1700
Data Index: 1851494 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.0079. Min Act: -0.1700
Data Index: 8699839 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.0079. Min Act: -0.1700
Data Index: 8373999 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3516. Min Range: -7.3516
Max Act: 7.0079. Min Act: -0.1700
Data Index: 8820006 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3516. Min Range: -7.3516
Max Act: 6.9766. Min Act: -0.1700
Data Index: 2791461 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3516. Min Range: -7.3516
Max Act: 6.9766. Min Act: -0.1700
Data Index: 6434636 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3516. Min Range: -7.3516
Max Act: 6.9454. Min Act: -0.1700
Data Index: 135011 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3516. Min Range: -7.3516
Max Act: 6.9766. Min Act: -0.1700
Data Index: 5279517 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3516. Min Range: -7.3516
Max Act: 6.9454. Min Act: -0.1700
Data Index: 1409849 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3516. Min Range: -7.3516
Max Act: 6.9141. Min Act: -0.1700
Data Index: 8313529 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19