Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2437. Min Range: -6.2437
Max Act: 6.2437. Min Act: -0.1700
Data Index: 7230890 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2437. Min Range: -6.2437
Max Act: 6.1187. Min Act: -0.1700
Data Index: 875278 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2437. Min Range: -6.2437
Max Act: 6.0874. Min Act: -0.1700
Data Index: 921375 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2437. Min Range: -6.2437
Max Act: 6.0249. Min Act: -0.1700
Data Index: 4028626 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.9937. Min Act: -0.1700
Data Index: 4716080 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2695113 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.9624. Min Act: -0.1700
Data Index: 221977 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.9312. Min Act: -0.1700
Data Index: 8575939 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8999. Min Act: -0.1700
Data Index: 5481628 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8687. Min Act: -0.1700
Data Index: 6444484 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8999. Min Act: -0.1700
Data Index: 3638934 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8687. Min Act: -0.1700
Data Index: 534547 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8687. Min Act: -0.1700
Data Index: 5998320 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8374. Min Act: -0.1700
Data Index: 603875 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8374. Min Act: -0.1700
Data Index: 1906076 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8374. Min Act: -0.1700
Data Index: 1687178 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8374. Min Act: -0.1700
Data Index: 7478551 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8374. Min Act: -0.1700
Data Index: 7264336 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8374. Min Act: -0.1700
Data Index: 5437723 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2437. Min Range: -6.2437
Max Act: 5.8062. Min Act: -0.1700
Data Index: 972495 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19