Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.5058. Min Act: -0.1700
Data Index: 1870033 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.3183. Min Act: -0.1700
Data Index: 6814314 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.2870. Min Act: -0.1700
Data Index: 4649425 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.2558. Min Act: -0.1700
Data Index: 4594393 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.2245. Min Act: -0.1700
Data Index: 5516096 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.2245. Min Act: -0.1700
Data Index: 8113181 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.1933. Min Act: -0.1700
Data Index: 5313761 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.1620. Min Act: -0.1700
Data Index: 6502729 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.1308. Min Act: -0.1700
Data Index: 4217383 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.1308. Min Act: -0.1700
Data Index: 1541984 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0683. Min Act: -0.1700
Data Index: 7376930 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0995. Min Act: -0.1700
Data Index: 8154458 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0683. Min Act: -0.1700
Data Index: 3810707 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0683. Min Act: -0.1700
Data Index: 3352497 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0683. Min Act: -0.1700
Data Index: 501313 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0683. Min Act: -0.1700
Data Index: 7518576 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0683. Min Act: -0.1700
Data Index: 152607 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0370. Min Act: -0.1700
Data Index: 503028 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0370. Min Act: -0.1700
Data Index: 3903293 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5058. Min Range: -7.5058
Max Act: 7.0370. Min Act: -0.1700
Data Index: 5485255 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19