Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6176 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.3491. Min Act: -0.1700
Data Index: 1359160 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.2866. Min Act: -0.1700
Data Index: 2285609 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.2241. Min Act: -0.1700
Data Index: 4617528 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.0991. Min Act: -0.1700
Data Index: 166902 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.0991. Min Act: -0.1700
Data Index: 932449 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.0366. Min Act: -0.1700
Data Index: 4164495 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.0366. Min Act: -0.1700
Data Index: 6836016 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.0366. Min Act: -0.1700
Data Index: 4080960 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.0991. Min Act: -0.1700
Data Index: 6039012 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.9741. Min Act: -0.1700
Data Index: 4513415 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.9741. Min Act: -0.1700
Data Index: 8719166 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.9741. Min Act: -0.1700
Data Index: 7177664 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3491. Min Range: -8.3491
Max Act: 8.0366. Min Act: -0.1700
Data Index: 3424490 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.9116. Min Act: -0.1700
Data Index: 5230985 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.8491. Min Act: -0.1700
Data Index: 16089 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.8491. Min Act: -0.1700
Data Index: 5103296 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.8491. Min Act: -0.1700
Data Index: 7206234 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.8491. Min Act: -0.1700
Data Index: 2497489 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.8491. Min Act: -0.1700
Data Index: 2629764 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3491. Min Range: -8.3491
Max Act: 7.8491. Min Act: -0.1700
Data Index: 7400182 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19