Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 697 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2369. Min Range: -6.2369
Max Act: 6.2369. Min Act: -0.1700
Data Index: 3839545 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2369. Min Range: -6.2369
Max Act: 6.0807. Min Act: -0.1700
Data Index: 1096492 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2369. Min Range: -6.2369
Max Act: 6.0494. Min Act: -0.1700
Data Index: 5178920 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.9557. Min Act: -0.1700
Data Index: 1636962 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.9557. Min Act: -0.1700
Data Index: 1872468 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.9557. Min Act: -0.1700
Data Index: 909902 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.9244. Min Act: -0.1700
Data Index: 3765170 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7682. Min Act: -0.1700
Data Index: 4869872 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7994. Min Act: -0.1700
Data Index: 6563513 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7682. Min Act: -0.1700
Data Index: 5707824 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7682. Min Act: -0.1700
Data Index: 1891704 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7369. Min Act: -0.1700
Data Index: 5691010 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7682. Min Act: -0.1700
Data Index: 6795161 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7369. Min Act: -0.1700
Data Index: 6651042 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7057. Min Act: -0.1700
Data Index: 3451665 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7369. Min Act: -0.1700
Data Index: 2733255 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7369. Min Act: -0.1700
Data Index: 5940938 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7057. Min Act: -0.1700
Data Index: 4640470 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.7057. Min Act: -0.1700
Data Index: 3538371 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2369. Min Range: -6.2369
Max Act: 5.6744. Min Act: -0.1700
Data Index: 4392158 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19