Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4373 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.9160. Min Act: -0.1700
Data Index: 4331076 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.7598. Min Act: -0.1700
Data Index: 7099401 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.6035. Min Act: -0.1700
Data Index: 5276136 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.5723. Min Act: -0.1700
Data Index: 3312711 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4785. Min Act: -0.1700
Data Index: 1966783 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.5098. Min Act: -0.1700
Data Index: 6770616 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4473. Min Act: -0.1700
Data Index: 1743251 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.5098. Min Act: -0.1700
Data Index: 3836124 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4160. Min Act: -0.1700
Data Index: 5663932 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4473. Min Act: -0.1700
Data Index: 4177032 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4160. Min Act: -0.1700
Data Index: 5375732 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4160. Min Act: -0.1700
Data Index: 815544 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4160. Min Act: -0.1700
Data Index: 3082079 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.4160. Min Act: -0.1700
Data Index: 6828013 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.3223. Min Act: -0.1700
Data Index: 4048774 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.3223. Min Act: -0.1700
Data Index: 5636418 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.2910. Min Act: -0.1700
Data Index: 6173589 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.2910. Min Act: -0.1700
Data Index: 3043998 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.2910. Min Act: -0.1700
Data Index: 5483965 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9160. Min Range: -6.9160
Max Act: 6.2598. Min Act: -0.1700
Data Index: 1737862 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19