Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4067 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4716. Min Range: -10.4716
Max Act: 10.4716. Min Act: -0.1700
Data Index: 133622 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4716. Min Range: -10.4716
Max Act: 10.2841. Min Act: -0.1700
Data Index: 6109016 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4716. Min Range: -10.4716
Max Act: 10.2841. Min Act: -0.1700
Data Index: 530643 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.9716. Min Act: -0.1700
Data Index: 2955624 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.9716. Min Act: -0.1700
Data Index: 7765665 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.9091. Min Act: -0.1700
Data Index: 3755578 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.9091. Min Act: -0.1700
Data Index: 7761997 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.9091. Min Act: -0.1700
Data Index: 2399029 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.9091. Min Act: -0.1700
Data Index: 2322936 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.8466. Min Act: -0.1700
Data Index: 3525908 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.7841. Min Act: -0.1700
Data Index: 999667 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.7841. Min Act: -0.1700
Data Index: 4987786 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.7216. Min Act: -0.1700
Data Index: 4627857 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.6591. Min Act: -0.1700
Data Index: 291640 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.6591. Min Act: -0.1700
Data Index: 5449182 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.6591. Min Act: -0.1700
Data Index: 5950911 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.6591. Min Act: -0.1700
Data Index: 7800079 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.6591. Min Act: -0.1700
Data Index: 4151815 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.5966. Min Act: -0.1700
Data Index: 5682279 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4716. Min Range: -10.4716
Max Act: 9.5966. Min Act: -0.1700
Data Index: 3124776 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19