Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5619 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.4008. Min Act: -0.1700
Data Index: 2688625 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.3517. Min Act: -0.1700
Data Index: 247469 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.3517. Min Act: -0.1700
Data Index: 1625572 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.3353. Min Act: -0.1700
Data Index: 2688623 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2860. Min Act: -0.1700
Data Index: 1648959 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2695. Min Act: -0.1700
Data Index: 7103798 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2530. Min Act: -0.1700
Data Index: 4620966 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2530. Min Act: -0.1700
Data Index: 3716890 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2530. Min Act: -0.1700
Data Index: 6014240 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2530. Min Act: -0.1700
Data Index: 6659364 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2530. Min Act: -0.1700
Data Index: 5363935 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2365. Min Act: -0.1700
Data Index: 5781745 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2365. Min Act: -0.1700
Data Index: 2133096 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2365. Min Act: -0.1700
Data Index: 6889738 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2199. Min Act: -0.1700
Data Index: 1016444 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2199. Min Act: -0.1700
Data Index: 7363802 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2199. Min Act: -0.1699
Data Index: 8416890 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2034. Min Act: -0.1700
Data Index: 960370 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2034. Min Act: -0.1700
Data Index: 5211537 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4008. Min Range: -2.4008
Max Act: 2.2034. Min Act: -0.1700
Data Index: 1913554 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19