Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4955. Min Range: -6.4955
Max Act: 6.4955. Min Act: -0.1700
Data Index: 213190 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4955. Min Range: -6.4955
Max Act: 6.4330. Min Act: -0.1700
Data Index: 8591738 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4955. Min Range: -6.4955
Max Act: 6.3705. Min Act: -0.1700
Data Index: 5836277 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4955. Min Range: -6.4955
Max Act: 6.0267. Min Act: -0.1700
Data Index: 531501 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4955. Min Range: -6.4955
Max Act: 6.0267. Min Act: -0.1700
Data Index: 8594931 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9955. Min Act: -0.1700
Data Index: 7742136 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9955. Min Act: -0.1700
Data Index: 3378972 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9642. Min Act: -0.1700
Data Index: 4904275 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9642. Min Act: -0.1700
Data Index: 6853406 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9642. Min Act: -0.1700
Data Index: 8109037 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9330. Min Act: -0.1700
Data Index: 4365108 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.8705. Min Act: -0.1700
Data Index: 7623949 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9017. Min Act: -0.1700
Data Index: 8181136 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9017. Min Act: -0.1700
Data Index: 5556882 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9017. Min Act: -0.1700
Data Index: 617289 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9017. Min Act: -0.1700
Data Index: 2448854 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.9017. Min Act: -0.1700
Data Index: 3979764 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.8705. Min Act: -0.1700
Data Index: 7103289 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.8392. Min Act: -0.1700
Data Index: 587568 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4955. Min Range: -6.4955
Max Act: 5.8392. Min Act: -0.1700
Data Index: 4323148 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19