Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5219 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1677. Min Act: -0.1700
Data Index: 477840 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1677. Min Act: -0.1700
Data Index: 2984757 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1677. Min Act: -0.1700
Data Index: 4683862 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1677. Min Act: -0.1700
Data Index: 66329 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1677. Min Act: -0.1700
Data Index: 3694336 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1052. Min Act: -0.1700
Data Index: 6964854 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1677. Min Act: -0.1700
Data Index: 3930296 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1052. Min Act: -0.1700
Data Index: 7650164 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1052. Min Act: -0.1700
Data Index: 329254 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.0427. Min Act: -0.1700
Data Index: 7770091 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1052. Min Act: -0.1700
Data Index: 4564963 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1052. Min Act: -0.1700
Data Index: 6191194 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1052. Min Act: -0.1700
Data Index: 5925789 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.0427. Min Act: -0.1700
Data Index: 1556298 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.0427. Min Act: -0.1700
Data Index: 1488786 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1677. Min Range: -10.1677
Max Act: 9.9802. Min Act: -0.1700
Data Index: 3154191 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.1052. Min Act: -0.1700
Data Index: 4710663 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.0427. Min Act: -0.1700
Data Index: 3291601 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1677. Min Range: -10.1677
Max Act: 9.9802. Min Act: -0.1700
Data Index: 2571520 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1677. Min Range: -10.1677
Max Act: 10.0427. Min Act: -0.1700
Data Index: 2538507 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19