Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0478. Min Range: -7.0478
Max Act: 7.0478. Min Act: -0.1700
Data Index: 5996423 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0478. Min Range: -7.0478
Max Act: 7.0478. Min Act: -0.1700
Data Index: 8450393 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0478. Min Range: -7.0478
Max Act: 7.0165. Min Act: -0.1700
Data Index: 2145486 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.9853. Min Act: -0.1700
Data Index: 8341327 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.8915. Min Act: -0.1700
Data Index: 3814918 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.8603. Min Act: -0.1700
Data Index: 6081743 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.8603. Min Act: -0.1700
Data Index: 3785419 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.8915. Min Act: -0.1700
Data Index: 1822741 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7978. Min Act: -0.1700
Data Index: 4491312 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7665. Min Act: -0.1700
Data Index: 4713910 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7665. Min Act: -0.1700
Data Index: 3755287 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7353. Min Act: -0.1700
Data Index: 669258 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7040. Min Act: -0.1700
Data Index: 150742 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7040. Min Act: -0.1700
Data Index: 7860592 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7040. Min Act: -0.1700
Data Index: 4436188 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.7353. Min Act: -0.1700
Data Index: 3877786 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.6415. Min Act: -0.1700
Data Index: 4084348 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.6415. Min Act: -0.1700
Data Index: 6513122 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.6103. Min Act: -0.1700
Data Index: 2885078 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0478. Min Range: -7.0478
Max Act: 6.6103. Min Act: -0.1700
Data Index: 6740595 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19