Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5448 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.5072. Min Act: -0.1700
Data Index: 5383178 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.5072. Min Act: -0.1700
Data Index: 2849798 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.3510. Min Act: -0.1700
Data Index: 6197346 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.3197. Min Act: -0.1700
Data Index: 587750 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.2885. Min Act: -0.1700
Data Index: 5706101 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.2572. Min Act: -0.1700
Data Index: 5215687 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.1635. Min Act: -0.1700
Data Index: 7206653 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.1322. Min Act: -0.1700
Data Index: 7246101 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.1010. Min Act: -0.1700
Data Index: 7547863 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.1010. Min Act: -0.1700
Data Index: 3771482 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.1010. Min Act: -0.1700
Data Index: 774374 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.1010. Min Act: -0.1700
Data Index: 5855226 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.1010. Min Act: -0.1700
Data Index: 7532964 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.0697. Min Act: -0.1700
Data Index: 1175562 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.0697. Min Act: -0.1700
Data Index: 3000514 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.0697. Min Act: -0.1700
Data Index: 1656028 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.0697. Min Act: -0.1700
Data Index: 2335965 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.0697. Min Act: -0.1700
Data Index: 5443120 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.0072. Min Act: -0.1700
Data Index: 1791194 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5072. Min Range: -5.5072
Max Act: 5.0385. Min Act: -0.1700
Data Index: 5045822 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19