Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1878 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.7579. Min Act: -0.1700
Data Index: 425018 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4767. Min Act: -0.1700
Data Index: 1541979 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4454. Min Act: -0.1700
Data Index: 4625989 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.3829. Min Act: -0.1700
Data Index: 2801659 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.3204. Min Act: -0.1700
Data Index: 2324030 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.2892. Min Act: -0.1700
Data Index: 8712181 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.2892. Min Act: -0.1700
Data Index: 4858434 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.2579. Min Act: -0.1700
Data Index: 3254145 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.2579. Min Act: -0.1700
Data Index: 554069 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.2579. Min Act: -0.1700
Data Index: 18599 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.2579. Min Act: -0.1700
Data Index: 1459566 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.2267. Min Act: -0.1700
Data Index: 5254978 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1642. Min Act: -0.1700
Data Index: 2519125 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1954. Min Act: -0.1700
Data Index: 3675508 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1954. Min Act: -0.1700
Data Index: 3233684 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1642. Min Act: -0.1700
Data Index: 6987439 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1017. Min Act: -0.1700
Data Index: 2601786 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1017. Min Act: -0.1700
Data Index: 5308172 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1329. Min Act: -0.1700
Data Index: 5163340 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.1017. Min Act: -0.1700
Data Index: 5218381 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19