Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5010 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0516. Min Range: -8.0516
Max Act: 8.0516. Min Act: -0.1700
Data Index: 3921780 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.7078. Min Act: -0.1700
Data Index: 3687969 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.6766. Min Act: -0.1700
Data Index: 5030422 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.6766. Min Act: -0.1700
Data Index: 4080127 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.6766. Min Act: -0.1700
Data Index: 1528325 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.5516. Min Act: -0.1700
Data Index: 1505225 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.5516. Min Act: -0.1700
Data Index: 522741 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.5203. Min Act: -0.1700
Data Index: 1842529 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.4578. Min Act: -0.1700
Data Index: 2672977 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.4266. Min Act: -0.1700
Data Index: 7041563 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3953. Min Act: -0.1700
Data Index: 6048216 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3953. Min Act: -0.1700
Data Index: 303188 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3328. Min Act: -0.1700
Data Index: 7875540 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3328. Min Act: -0.1700
Data Index: 8751270 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3328. Min Act: -0.1700
Data Index: 2672978 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3016. Min Act: -0.1700
Data Index: 2573686 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.3016. Min Act: -0.1700
Data Index: 4022152 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.2391. Min Act: -0.1700
Data Index: 7495822 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.2703. Min Act: -0.1700
Data Index: 8696092 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0516. Min Range: -8.0516
Max Act: 7.2703. Min Act: -0.1700
Data Index: 3309027 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19