Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.5891. Min Act: -0.1700
Data Index: 4117087 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.5266. Min Act: -0.1700
Data Index: 8804734 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.2141. Min Act: -0.1700
Data Index: 8680934 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.2141. Min Act: -0.1700
Data Index: 2892813 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.1516. Min Act: -0.1700
Data Index: 6140307 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.0891. Min Act: -0.1700
Data Index: 1569973 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.1516. Min Act: -0.1700
Data Index: 1588688 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.0891. Min Act: -0.1700
Data Index: 3088904 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.0266. Min Act: -0.1700
Data Index: 7400125 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.0266. Min Act: -0.1700
Data Index: 1099144 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5891. Min Range: -8.5891
Max Act: 7.9641. Min Act: -0.1700
Data Index: 1159021 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5891. Min Range: -8.5891
Max Act: 7.9641. Min Act: -0.1700
Data Index: 3066087 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.0266. Min Act: -0.1700
Data Index: 4039251 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.0266. Min Act: -0.1700
Data Index: 3725834 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5891. Min Range: -8.5891
Max Act: 8.0266. Min Act: -0.1700
Data Index: 716029 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5891. Min Range: -8.5891
Max Act: 7.9641. Min Act: -0.1700
Data Index: 2959400 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5891. Min Range: -8.5891
Max Act: 7.9641. Min Act: -0.1700
Data Index: 3319071 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5891. Min Range: -8.5891
Max Act: 7.8391. Min Act: -0.1700
Data Index: 1356993 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5891. Min Range: -8.5891
Max Act: 7.9016. Min Act: -0.1700
Data Index: 3935057 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5891. Min Range: -8.5891
Max Act: 7.9016. Min Act: -0.1700
Data Index: 4965322 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19