Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2572 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.6775. Min Act: -0.1700
Data Index: 6047118 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.5838. Min Act: -0.1700
Data Index: 6893533 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.4588. Min Act: -0.1700
Data Index: 7468176 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.4275. Min Act: -0.1700
Data Index: 5603699 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3963. Min Act: -0.1700
Data Index: 3367313 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3650. Min Act: -0.1700
Data Index: 4658062 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3338. Min Act: -0.1700
Data Index: 478791 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3338. Min Act: -0.1700
Data Index: 919103 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3025. Min Act: -0.1700
Data Index: 3367311 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3025. Min Act: -0.1700
Data Index: 3484640 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3025. Min Act: -0.1700
Data Index: 1678182 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2713. Min Act: -0.1700
Data Index: 4185710 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.3025. Min Act: -0.1700
Data Index: 5796981 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2713. Min Act: -0.1700
Data Index: 5461420 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2400. Min Act: -0.1700
Data Index: 4323282 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2400. Min Act: -0.1700
Data Index: 5796984 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2088. Min Act: -0.1700
Data Index: 3264 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2088. Min Act: -0.1700
Data Index: 4185711 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2088. Min Act: -0.1700
Data Index: 729106 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6775. Min Range: -5.6775
Max Act: 5.2088. Min Act: -0.1700
Data Index: 6865330 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19