Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5562. Min Range: -8.5562
Max Act: 8.5562. Min Act: -0.1700
Data Index: 2763301 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.9312. Min Act: -0.1700
Data Index: 2263690 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.6812. Min Act: -0.1700
Data Index: 2163317 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.6187. Min Act: -0.1700
Data Index: 8826630 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.6187. Min Act: -0.1700
Data Index: 8238877 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.6187. Min Act: -0.1700
Data Index: 3490077 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.6187. Min Act: -0.1700
Data Index: 6571205 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.6187. Min Act: -0.1700
Data Index: 5672114 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.5562. Min Act: -0.1700
Data Index: 8048218 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.5562. Min Act: -0.1700
Data Index: 7880531 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.5250. Min Act: -0.1700
Data Index: 3841990 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.5250. Min Act: -0.1700
Data Index: 8354807 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.4625. Min Act: -0.1700
Data Index: 402844 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.4937. Min Act: -0.1700
Data Index: 443470 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.4312. Min Act: -0.1700
Data Index: 6136895 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.4312. Min Act: -0.1700
Data Index: 1025906 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.4000. Min Act: -0.1700
Data Index: 7939738 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.4000. Min Act: -0.1700
Data Index: 4943996 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.3687. Min Act: -0.1700
Data Index: 8297087 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5562. Min Range: -8.5562
Max Act: 7.3375. Min Act: -0.1700
Data Index: 5655261 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19