Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1794. Min Range: -6.1794
Max Act: 6.1794. Min Act: -0.1700
Data Index: 3080256 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.9919. Min Act: -0.1700
Data Index: 267718 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.7419. Min Act: -0.1700
Data Index: 907680 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.7419. Min Act: -0.1700
Data Index: 146370 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.7107. Min Act: -0.1700
Data Index: 7681696 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6482. Min Act: -0.1700
Data Index: 7413686 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6482. Min Act: -0.1700
Data Index: 8041452 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6482. Min Act: -0.1700
Data Index: 446215 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6482. Min Act: -0.1700
Data Index: 539744 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6482. Min Act: -0.1700
Data Index: 7019433 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6169. Min Act: -0.1700
Data Index: 3035948 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6482. Min Act: -0.1700
Data Index: 6126565 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.6169. Min Act: -0.1700
Data Index: 5094945 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.5857. Min Act: -0.1700
Data Index: 5419771 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.5857. Min Act: -0.1700
Data Index: 6894223 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.5544. Min Act: -0.1700
Data Index: 5096765 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.5857. Min Act: -0.1700
Data Index: 401371 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.5857. Min Act: -0.1700
Data Index: 6269282 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.5544. Min Act: -0.1700
Data Index: 1135040 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1794. Min Range: -6.1794
Max Act: 5.5544. Min Act: -0.1700
Data Index: 7027570 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19