Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3737 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.5649. Min Act: -0.1700
Data Index: 1021885 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.2837. Min Act: -0.1700
Data Index: 1206134 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.2837. Min Act: -0.1700
Data Index: 1206135 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.2837. Min Act: -0.1700
Data Index: 6778526 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.2837. Min Act: -0.1700
Data Index: 6975143 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.2524. Min Act: -0.1700
Data Index: 4715764 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.2212. Min Act: -0.1700
Data Index: 2173661 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.1899. Min Act: -0.1700
Data Index: 7757175 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.1899. Min Act: -0.1700
Data Index: 6931934 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.1587. Min Act: -0.1700
Data Index: 4669144 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.1587. Min Act: -0.1700
Data Index: 4042047 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.1274. Min Act: -0.1700
Data Index: 4693648 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.0962. Min Act: -0.1700
Data Index: 3686803 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.0649. Min Act: -0.1700
Data Index: 4534217 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.0337. Min Act: -0.1700
Data Index: 2806604 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.0649. Min Act: -0.1700
Data Index: 1746411 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5649. Min Range: -7.5649
Max Act: 7.0024. Min Act: -0.1700
Data Index: 1446523 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5649. Min Range: -7.5649
Max Act: 6.9712. Min Act: -0.1700
Data Index: 5237866 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5649. Min Range: -7.5649
Max Act: 6.9712. Min Act: -0.1700
Data Index: 5648472 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5649. Min Range: -7.5649
Max Act: 6.9712. Min Act: -0.1700
Data Index: 7032997 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19