Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2818. Min Range: -8.2818
Max Act: 8.2818. Min Act: -0.1700
Data Index: 4554584 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2818. Min Range: -8.2818
Max Act: 8.0943. Min Act: -0.1700
Data Index: 3467237 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2818. Min Range: -8.2818
Max Act: 8.0318. Min Act: -0.1700
Data Index: 540159 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2818. Min Range: -8.2818
Max Act: 8.0318. Min Act: -0.1700
Data Index: 4995799 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.9693. Min Act: -0.1700
Data Index: 4330999 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.9693. Min Act: -0.1700
Data Index: 7177740 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.9068. Min Act: -0.1700
Data Index: 6826768 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.8443. Min Act: -0.1700
Data Index: 3885282 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7818. Min Act: -0.1700
Data Index: 923647 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7818. Min Act: -0.1700
Data Index: 1851838 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7818. Min Act: -0.1700
Data Index: 7743354 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7818. Min Act: -0.1700
Data Index: 1694829 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7818. Min Act: -0.1700
Data Index: 4290565 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7193. Min Act: -0.1700
Data Index: 182065 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7193. Min Act: -0.1700
Data Index: 6711562 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7193. Min Act: -0.1700
Data Index: 5145785 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7193. Min Act: -0.1700
Data Index: 4695531 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7193. Min Act: -0.1700
Data Index: 3969991 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.7193. Min Act: -0.1700
Data Index: 3389581 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2818. Min Range: -8.2818
Max Act: 7.5943. Min Act: -0.1700
Data Index: 5139404 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19