Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.4704. Min Act: -0.1700
Data Index: 4175699 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.4704. Min Act: -0.1700
Data Index: 3752893 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.2516. Min Act: -0.1700
Data Index: 5828460 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.1891. Min Act: -0.1700
Data Index: 7697617 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.1266. Min Act: -0.1700
Data Index: 407178 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0954. Min Act: -0.1700
Data Index: 6238833 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0641. Min Act: -0.1700
Data Index: 4113132 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0641. Min Act: -0.1700
Data Index: 5607288 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0641. Min Act: -0.1700
Data Index: 7279202 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0329. Min Act: -0.1700
Data Index: 3039208 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0016. Min Act: -0.1700
Data Index: 2218456 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0016. Min Act: -0.1700
Data Index: 444123 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4704. Min Range: -7.4704
Max Act: 6.9704. Min Act: -0.1700
Data Index: 2333030 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0016. Min Act: -0.1700
Data Index: 6838302 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4704. Min Range: -7.4704
Max Act: 7.0016. Min Act: -0.1700
Data Index: 6982849 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4704. Min Range: -7.4704
Max Act: 6.9391. Min Act: -0.1700
Data Index: 4665621 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4704. Min Range: -7.4704
Max Act: 6.9391. Min Act: -0.1700
Data Index: 4502759 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4704. Min Range: -7.4704
Max Act: 6.9079. Min Act: -0.1700
Data Index: 8413268 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4704. Min Range: -7.4704
Max Act: 6.9079. Min Act: -0.1700
Data Index: 256088 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4704. Min Range: -7.4704
Max Act: 6.9079. Min Act: -0.1700
Data Index: 7254495 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19