Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5510 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0223. Min Range: -7.0223
Max Act: 7.0223. Min Act: -0.1700
Data Index: 1786916 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0223. Min Range: -7.0223
Max Act: 7.0223. Min Act: -0.1700
Data Index: 7052359 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.8035. Min Act: -0.1700
Data Index: 6058709 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.8035. Min Act: -0.1700
Data Index: 4860022 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.8348. Min Act: -0.1700
Data Index: 5417777 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7723. Min Act: -0.1700
Data Index: 6912619 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7723. Min Act: -0.1700
Data Index: 6330213 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7723. Min Act: -0.1700
Data Index: 7197576 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7723. Min Act: -0.1700
Data Index: 4787213 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7723. Min Act: -0.1700
Data Index: 1554599 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7410. Min Act: -0.1700
Data Index: 8634589 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7410. Min Act: -0.1700
Data Index: 6049707 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7410. Min Act: -0.1700
Data Index: 2927917 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7410. Min Act: -0.1700
Data Index: 4137661 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7410. Min Act: -0.1700
Data Index: 1786550 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7410. Min Act: -0.1700
Data Index: 1784697 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7098. Min Act: -0.1700
Data Index: 1350083 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7098. Min Act: -0.1700
Data Index: 5259649 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.6785. Min Act: -0.1700
Data Index: 7918524 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0223. Min Range: -7.0223
Max Act: 6.7098. Min Act: -0.1700
Data Index: 6389645 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19