Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1741. Min Range: -8.1741
Max Act: 8.1741. Min Act: -0.1700
Data Index: 2683656 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.8928. Min Act: -0.1700
Data Index: 4441764 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.7991. Min Act: -0.1700
Data Index: 3219201 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.7366. Min Act: -0.1700
Data Index: 3293659 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.6116. Min Act: -0.1700
Data Index: 8672710 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.6116. Min Act: -0.1700
Data Index: 4741092 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.5803. Min Act: -0.1700
Data Index: 1999712 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.5491. Min Act: -0.1700
Data Index: 8811629 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.5491. Min Act: -0.1700
Data Index: 5948993 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.5491. Min Act: -0.1700
Data Index: 6030521 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.5491. Min Act: -0.1700
Data Index: 7681253 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.4553. Min Act: -0.1700
Data Index: 6465600 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.4241. Min Act: -0.1700
Data Index: 3696150 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.4553. Min Act: -0.1700
Data Index: 7864032 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.4241. Min Act: -0.1700
Data Index: 8056152 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.3928. Min Act: -0.1700
Data Index: 224549 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.3303. Min Act: -0.1700
Data Index: 3219203 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.3303. Min Act: -0.1700
Data Index: 579725 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.2678. Min Act: -0.1700
Data Index: 425260 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1741. Min Range: -8.1741
Max Act: 7.2678. Min Act: -0.1700
Data Index: 1759583 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19