Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2388 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1803. Min Range: -10.1803
Max Act: 10.1803. Min Act: -0.1700
Data Index: 6763560 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1803. Min Range: -10.1803
Max Act: 10.0553. Min Act: -0.1700
Data Index: 4391939 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.7428. Min Act: -0.1700
Data Index: 2672223 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.3053. Min Act: -0.1700
Data Index: 1277563 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.3053. Min Act: -0.1700
Data Index: 3495669 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.3053. Min Act: -0.1700
Data Index: 7095820 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1803. Min Act: -0.1700
Data Index: 8194440 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1803. Min Act: -0.1700
Data Index: 8436680 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 1044950 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1803. Min Act: -0.1700
Data Index: 5182157 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 4753244 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 7280699 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 3393556 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 4248376 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 2377443 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 203843 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.1178. Min Act: -0.1700
Data Index: 3035726 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.0553. Min Act: -0.1700
Data Index: 3178726 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.0553. Min Act: -0.1700
Data Index: 5967258 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1803. Min Range: -10.1803
Max Act: 9.0553. Min Act: -0.1700
Data Index: 3726829 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19