Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.8170. Min Act: -0.1700
Data Index: 6766480 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.3630. Min Act: -0.1700
Data Index: 258040 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.3002. Min Act: -0.1700
Data Index: 2041059 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.2688. Min Act: -0.1700
Data Index: 6222783 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.2060. Min Act: -0.1700
Data Index: 1004139 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.2217. Min Act: -0.1700
Data Index: 1834795 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1902. Min Act: -0.1700
Data Index: 5379310 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1902. Min Act: -0.1700
Data Index: 1884913 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1745. Min Act: -0.1700
Data Index: 6566861 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1588. Min Act: -0.1700
Data Index: 2974854 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1430. Min Act: -0.1700
Data Index: 8519437 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1115. Min Act: -0.1700
Data Index: 8129440 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1430. Min Act: -0.1700
Data Index: 2318895 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1273. Min Act: -0.1700
Data Index: 6486522 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1115. Min Act: -0.1700
Data Index: 3697857 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1115. Min Act: -0.1700
Data Index: 2106792 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.0958. Min Act: -0.1700
Data Index: 1690027 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.0958. Min Act: -0.1700
Data Index: 6279722 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.0800. Min Act: -0.1700
Data Index: 3593107 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8170. Min Range: -3.8170
Max Act: 3.1273. Min Act: -0.1700
Data Index: 4441711 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19