Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 753 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1308. Min Range: -7.1308
Max Act: 7.1308. Min Act: -0.1700
Data Index: 2508697 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.7245. Min Act: -0.1700
Data Index: 416166 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.5370. Min Act: -0.1700
Data Index: 8589354 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.4433. Min Act: -0.1700
Data Index: 2089035 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.3495. Min Act: -0.1700
Data Index: 3027455 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.3495. Min Act: -0.1700
Data Index: 2116133 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.3183. Min Act: -0.1700
Data Index: 5257910 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.2558. Min Act: -0.1700
Data Index: 6308823 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.1933. Min Act: -0.1700
Data Index: 4973297 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.1620. Min Act: -0.1700
Data Index: 6591738 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.1620. Min Act: -0.1700
Data Index: 2816780 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.1308. Min Act: -0.1700
Data Index: 7541229 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0995. Min Act: -0.1700
Data Index: 8369082 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0995. Min Act: -0.1700
Data Index: 3224661 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0995. Min Act: -0.1700
Data Index: 764564 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0995. Min Act: -0.1700
Data Index: 2407214 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0683. Min Act: -0.1700
Data Index: 4198846 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0683. Min Act: -0.1700
Data Index: 973132 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0370. Min Act: -0.1700
Data Index: 1386908 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1308. Min Range: -7.1308
Max Act: 6.0058. Min Act: -0.1700
Data Index: 3980738 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19