Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 220 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0267. Min Range: -8.0267
Max Act: 8.0267. Min Act: -0.1700
Data Index: 5617289 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.6829. Min Act: -0.1700
Data Index: 5058993 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.4329. Min Act: -0.1700
Data Index: 8021362 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.2142. Min Act: -0.1700
Data Index: 2400434 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.1204. Min Act: -0.1700
Data Index: 3552925 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.0267. Min Act: -0.1700
Data Index: 6711330 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.9954. Min Act: -0.1700
Data Index: 405763 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.8392. Min Act: -0.1700
Data Index: 4451573 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.8704. Min Act: -0.1700
Data Index: 5022334 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.8392. Min Act: -0.1700
Data Index: 7657439 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.8079. Min Act: -0.1700
Data Index: 2903865 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.7767. Min Act: -0.1700
Data Index: 7715168 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.7767. Min Act: -0.1700
Data Index: 6830790 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.7767. Min Act: -0.1700
Data Index: 5417468 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.7767. Min Act: -0.1700
Data Index: 7799122 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.6517. Min Act: -0.1700
Data Index: 4493696 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.6829. Min Act: -0.1700
Data Index: 1615968 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.6517. Min Act: -0.1700
Data Index: 5704972 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.6829. Min Act: -0.1700
Data Index: 7913281 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0267. Min Range: -8.0267
Max Act: 6.6517. Min Act: -0.1700
Data Index: 6911679 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19