Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1875. Min Range: -7.1875
Max Act: 7.1875. Min Act: -0.1700
Data Index: 8621354 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1875. Min Range: -7.1875
Max Act: 7.0937. Min Act: -0.1700
Data Index: 835300 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1875. Min Range: -7.1875
Max Act: 7.0000. Min Act: -0.1700
Data Index: 8237642 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.9062. Min Act: -0.1700
Data Index: 6361905 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.8437. Min Act: -0.1700
Data Index: 22450 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.8437. Min Act: -0.1700
Data Index: 1442197 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.7187. Min Act: -0.1700
Data Index: 6810691 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6875. Min Act: -0.1700
Data Index: 4591724 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6875. Min Act: -0.1700
Data Index: 3266347 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6875. Min Act: -0.1700
Data Index: 1102173 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.7187. Min Act: -0.1700
Data Index: 6388598 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6562. Min Act: -0.1700
Data Index: 4333859 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6562. Min Act: -0.1700
Data Index: 5468440 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6562. Min Act: -0.1700
Data Index: 7458311 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6562. Min Act: -0.1700
Data Index: 6562389 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6250. Min Act: -0.1700
Data Index: 1959884 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6250. Min Act: -0.1700
Data Index: 2245134 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6250. Min Act: -0.1700
Data Index: 7401561 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6250. Min Act: -0.1700
Data Index: 5298132 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1875. Min Range: -7.1875
Max Act: 6.6250. Min Act: -0.1700
Data Index: 6613165 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19