Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 468 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.7141. Min Act: -0.1700
Data Index: 3224040 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.6829. Min Act: -0.1700
Data Index: 7777942 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.5266. Min Act: -0.1700
Data Index: 4850227 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.3391. Min Act: -0.1700
Data Index: 4863375 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.2766. Min Act: -0.1700
Data Index: 3523601 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.2766. Min Act: -0.1700
Data Index: 2126619 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.2454. Min Act: -0.1700
Data Index: 6649034 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1828. Min Act: -0.1700
Data Index: 2509586 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1516. Min Act: -0.1700
Data Index: 1011842 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1516. Min Act: -0.1700
Data Index: 2816160 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 6992674 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 5571943 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 923818 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 5356166 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 1264826 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 1973106 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.0578. Min Act: -0.1700
Data Index: 2181861 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.0578. Min Act: -0.1700
Data Index: 5154065 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7141. Min Range: -4.7141
Max Act: 3.9953. Min Act: -0.1700
Data Index: 6625439 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7141. Min Range: -4.7141
Max Act: 4.0578. Min Act: -0.1700
Data Index: 3764031 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19