Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.9418. Min Act: -0.1700
Data Index: 5165883 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.8793. Min Act: -0.1700
Data Index: 4130873 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.5981. Min Act: -0.1700
Data Index: 8711520 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.4418. Min Act: -0.1700
Data Index: 6506315 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.3793. Min Act: -0.1700
Data Index: 5312178 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.3168. Min Act: -0.1700
Data Index: 143321 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2543. Min Act: -0.1700
Data Index: 3888835 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2543. Min Act: -0.1700
Data Index: 6793716 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.1918. Min Act: -0.1700
Data Index: 5373478 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2231. Min Act: -0.1700
Data Index: 1694696 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2231. Min Act: -0.1700
Data Index: 4711924 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2231. Min Act: -0.1700
Data Index: 3043143 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2231. Min Act: -0.1700
Data Index: 5950819 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2231. Min Act: -0.1700
Data Index: 5643503 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2231. Min Act: -0.1700
Data Index: 3253910 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.2231. Min Act: -0.1700
Data Index: 7708895 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.1918. Min Act: -0.1700
Data Index: 7128369 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.1918. Min Act: -0.1700
Data Index: 2697459 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6156356 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9418. Min Range: -6.9418
Max Act: 6.1918. Min Act: -0.1700
Data Index: 2256809 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19