Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.6916. Min Act: -0.1700
Data Index: 8794513 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.5666. Min Act: -0.1700
Data Index: 2047718 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.5666. Min Act: -0.1700
Data Index: 4258508 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.5041. Min Act: -0.1700
Data Index: 7257040 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.5041. Min Act: -0.1700
Data Index: 3747483 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.4416. Min Act: -0.1700
Data Index: 7257039 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.4416. Min Act: -0.1700
Data Index: 4258507 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.2541. Min Act: -0.1700
Data Index: 2552672 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.1916. Min Act: -0.1700
Data Index: 1107000 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.1916. Min Act: -0.1700
Data Index: 8737801 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.1291. Min Act: -0.1700
Data Index: 1106985 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.1916. Min Act: -0.1700
Data Index: 4686289 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.1291. Min Act: -0.1700
Data Index: 2468772 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 3931333 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 4777425 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 6509678 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 6734770 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 1106993 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 7746168 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6916. Min Range: -9.6916
Max Act: 9.0666. Min Act: -0.1700
Data Index: 6940591 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19