Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5531 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.5014. Min Act: -0.1700
Data Index: 7382744 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.4702. Min Act: -0.1700
Data Index: 632776 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.4702. Min Act: -0.1700
Data Index: 5053328 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.4389. Min Act: -0.1700
Data Index: 3001073 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.3139. Min Act: -0.1700
Data Index: 8202420 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.2827. Min Act: -0.1700
Data Index: 6430003 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.2514. Min Act: -0.1700
Data Index: 1593579 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1889. Min Act: -0.1700
Data Index: 4099242 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1889. Min Act: -0.1700
Data Index: 3664648 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1577. Min Act: -0.1700
Data Index: 2144779 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 336735 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 5684299 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 3039764 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0952. Min Act: -0.1700
Data Index: 2312269 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0952. Min Act: -0.1700
Data Index: 1468116 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0952. Min Act: -0.1700
Data Index: 5050527 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.1264. Min Act: -0.1700
Data Index: 3552743 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0639. Min Act: -0.1700
Data Index: 2926795 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0639. Min Act: -0.1700
Data Index: 8575235 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5014. Min Range: -6.5014
Max Act: 6.0639. Min Act: -0.1700
Data Index: 6161392 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19