Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3870 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6259. Min Range: -6.6259
Max Act: 6.6259. Min Act: -0.1700
Data Index: 4005395 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6259. Min Range: -6.6259
Max Act: 6.3134. Min Act: -0.1700
Data Index: 3959760 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6259. Min Range: -6.6259
Max Act: 6.2197. Min Act: -0.1700
Data Index: 7573544 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6259. Min Range: -6.6259
Max Act: 6.1884. Min Act: -0.1700
Data Index: 1142174 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6259. Min Range: -6.6259
Max Act: 6.1884. Min Act: -0.1700
Data Index: 4045520 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6259. Min Range: -6.6259
Max Act: 6.1572. Min Act: -0.1700
Data Index: 1316450 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.9697. Min Act: -0.1700
Data Index: 3527387 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.9697. Min Act: -0.1700
Data Index: 8230495 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.9697. Min Act: -0.1700
Data Index: 6768231 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6259. Min Range: -6.6259
Max Act: 6.0009. Min Act: -0.1700
Data Index: 6042274 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.9384. Min Act: -0.1700
Data Index: 2410880 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.9072. Min Act: -0.1700
Data Index: 8166078 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.9072. Min Act: -0.1700
Data Index: 6913238 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.8759. Min Act: -0.1700
Data Index: 2914998 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.8759. Min Act: -0.1700
Data Index: 4872056 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.8759. Min Act: -0.1700
Data Index: 5116309 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5083391 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5987193 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.8447. Min Act: -0.1700
Data Index: 1637261 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6259. Min Range: -6.6259
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5940146 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19