Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3922 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1558. Min Range: -7.1558
Max Act: 7.1245. Min Act: -0.1700
Data Index: 2622324 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1558. Min Range: -7.1558
Max Act: 7.1245. Min Act: -0.1700
Data Index: 2276640 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1558. Min Range: -7.1558
Max Act: 7.1558. Min Act: -0.1700
Data Index: 6137794 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.9995. Min Act: -0.1700
Data Index: 2252238 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.9995. Min Act: -0.1700
Data Index: 1655914 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.9370. Min Act: -0.1700
Data Index: 602005 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.9370. Min Act: -0.1700
Data Index: 7908577 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.9058. Min Act: -0.1700
Data Index: 4961730 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.8745. Min Act: -0.1700
Data Index: 4658407 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.8745. Min Act: -0.1700
Data Index: 606567 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.8433. Min Act: -0.1700
Data Index: 7893740 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.8120. Min Act: -0.1700
Data Index: 1900578 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.7495. Min Act: -0.1700
Data Index: 5931762 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.7495. Min Act: -0.1700
Data Index: 3038161 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.7183. Min Act: -0.1700
Data Index: 5820823 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.7183. Min Act: -0.1700
Data Index: 4957828 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.7183. Min Act: -0.1700
Data Index: 311564 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.7183. Min Act: -0.1700
Data Index: 3288182 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.6870. Min Act: -0.1700
Data Index: 2016952 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1558. Min Range: -7.1558
Max Act: 6.6558. Min Act: -0.1700
Data Index: 1595432 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19