Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 184 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0264. Min Range: -7.0264
Max Act: 7.0264. Min Act: -0.1700
Data Index: 1229206 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.6202. Min Act: -0.1700
Data Index: 6659803 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.4327. Min Act: -0.1700
Data Index: 5806431 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.4014. Min Act: -0.1700
Data Index: 3952113 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.4014. Min Act: -0.1700
Data Index: 5033483 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.3389. Min Act: -0.1700
Data Index: 6996227 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.3389. Min Act: -0.1700
Data Index: 3557984 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.3077. Min Act: -0.1700
Data Index: 684763 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.3077. Min Act: -0.1700
Data Index: 666083 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.3077. Min Act: -0.1700
Data Index: 2930631 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.3077. Min Act: -0.1700
Data Index: 6681814 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.2764. Min Act: -0.1700
Data Index: 648799 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.2452. Min Act: -0.1700
Data Index: 2327700 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.2764. Min Act: -0.1700
Data Index: 6549026 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.2139. Min Act: -0.1700
Data Index: 8679990 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.2139. Min Act: -0.1700
Data Index: 7885942 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.2139. Min Act: -0.1700
Data Index: 7399153 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.2139. Min Act: -0.1700
Data Index: 4478867 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.1827. Min Act: -0.1700
Data Index: 7732438 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0264. Min Range: -7.0264
Max Act: 6.1827. Min Act: -0.1700
Data Index: 5598977 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19