Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.3087. Min Act: -0.1700
Data Index: 6457450 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.2462. Min Act: -0.1700
Data Index: 7605135 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.1837. Min Act: -0.1700
Data Index: 623026 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.1837. Min Act: -0.1700
Data Index: 2283880 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.1837. Min Act: -0.1700
Data Index: 1580392 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.1212. Min Act: -0.1700
Data Index: 466531 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.1212. Min Act: -0.1700
Data Index: 3708648 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 8802674 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.1212. Min Act: -0.1700
Data Index: 1510697 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 1194191 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 5018007 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 7603926 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 268490 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 6951745 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 2409724 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3087. Min Range: -8.3087
Max Act: 8.0587. Min Act: -0.1700
Data Index: 5947720 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3087. Min Range: -8.3087
Max Act: 7.9962. Min Act: -0.1700
Data Index: 2002686 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3087. Min Range: -8.3087
Max Act: 7.9962. Min Act: -0.1700
Data Index: 4231032 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3087. Min Range: -8.3087
Max Act: 7.9337. Min Act: -0.1700
Data Index: 4442510 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3087. Min Range: -8.3087
Max Act: 7.9962. Min Act: -0.1700
Data Index: 5266372 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19