Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0376. Min Range: -5.0376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 1784196 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.9438. Min Act: -0.1700
Data Index: 2601460 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.9438. Min Act: -0.1700
Data Index: 2601458 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.9126. Min Act: -0.1700
Data Index: 2498152 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.9126. Min Act: -0.1700
Data Index: 4443336 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.8501. Min Act: -0.1700
Data Index: 8638405 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.8188. Min Act: -0.1700
Data Index: 6554338 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.6938. Min Act: -0.1700
Data Index: 5262930 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.6313. Min Act: -0.1700
Data Index: 3356241 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.6001. Min Act: -0.1700
Data Index: 8070344 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.6313. Min Act: -0.1700
Data Index: 1977757 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.6001. Min Act: -0.1700
Data Index: 54996 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.5688. Min Act: -0.1700
Data Index: 6637691 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.5375. Min Act: -0.1700
Data Index: 3841520 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.5375. Min Act: -0.1700
Data Index: 4174973 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.5375. Min Act: -0.1700
Data Index: 143178 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.4438. Min Act: -0.1700
Data Index: 3832179 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.4750. Min Act: -0.1700
Data Index: 2120524 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.4750. Min Act: -0.1700
Data Index: 8199834 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0376. Min Range: -5.0376
Max Act: 4.4438. Min Act: -0.1700
Data Index: 271839 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19