Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1791 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.4891. Min Act: -0.1700
Data Index: 6137045 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.4266. Min Act: -0.1700
Data Index: 3171161 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.4266. Min Act: -0.1700
Data Index: 4702973 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.3641. Min Act: -0.1700
Data Index: 6784724 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.3641. Min Act: -0.1700
Data Index: 8626636 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.2704. Min Act: -0.1700
Data Index: 939274 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.3641. Min Act: -0.1700
Data Index: 8598591 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.2704. Min Act: -0.1700
Data Index: 2022459 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.2391. Min Act: -0.1700
Data Index: 3478265 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.2391. Min Act: -0.1700
Data Index: 3691833 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.2391. Min Act: -0.1700
Data Index: 5536633 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.2079. Min Act: -0.1700
Data Index: 63954 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.2079. Min Act: -0.1700
Data Index: 2354356 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.1766. Min Act: -0.1700
Data Index: 2367673 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.1454. Min Act: -0.1700
Data Index: 5031112 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.1454. Min Act: -0.1700
Data Index: 1880779 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.1141. Min Act: -0.1700
Data Index: 2428963 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.0829. Min Act: -0.1700
Data Index: 7956972 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.0516. Min Act: -0.1700
Data Index: 7803787 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4891. Min Range: -7.4891
Max Act: 7.0516. Min Act: -0.1700
Data Index: 4237703 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19