Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.7751. Min Act: -0.1700
Data Index: 2423226 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.7126. Min Act: -0.1700
Data Index: 2642117 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.6188. Min Act: -0.1700
Data Index: 4295163 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.5876. Min Act: -0.1700
Data Index: 5386853 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.5251. Min Act: -0.1700
Data Index: 107166 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.4626. Min Act: -0.1700
Data Index: 3046925 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.3688. Min Act: -0.1700
Data Index: 5991876 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.3376. Min Act: -0.1700
Data Index: 8660657 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.3376. Min Act: -0.1700
Data Index: 8816330 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.3063. Min Act: -0.1700
Data Index: 2390853 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.2751. Min Act: -0.1700
Data Index: 6073075 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.2438. Min Act: -0.1700
Data Index: 5150965 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.2126. Min Act: -0.1700
Data Index: 2101439 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.2126. Min Act: -0.1700
Data Index: 1393168 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.2126. Min Act: -0.1700
Data Index: 5299855 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.2438. Min Act: -0.1700
Data Index: 2616517 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.1813. Min Act: -0.1700
Data Index: 7373960 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.1813. Min Act: -0.1700
Data Index: 445566 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.1813. Min Act: -0.1700
Data Index: 6914113 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7751. Min Range: -5.7751
Max Act: 5.1188. Min Act: -0.1700
Data Index: 7141753 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19