Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8482. Min Range: -11.8482
Max Act: 11.8482. Min Act: -0.1700
Data Index: 6884600 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.7857. Min Act: -0.1700
Data Index: 7472733 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.7857. Min Act: -0.1694
Data Index: 6330094 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.5357. Min Act: -0.1700
Data Index: 1685718 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.4107. Min Act: -0.1700
Data Index: 2338637 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.4107. Min Act: -0.1700
Data Index: 1285226 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.4107. Min Act: -0.1700
Data Index: 3762997 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.3482. Min Act: -0.1700
Data Index: 972742 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.2857. Min Act: -0.1700
Data Index: 1397656 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.3482. Min Act: -0.1700
Data Index: 972770 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.0982. Min Act: -0.1700
Data Index: 4141618 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.0357. Min Act: -0.1700
Data Index: 4879816 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.0357. Min Act: -0.1697
Data Index: 427602 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8482. Min Range: -11.8482
Max Act: 9.9732. Min Act: -0.1700
Data Index: 2302624 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8482. Min Range: -11.8482
Max Act: 10.0357. Min Act: -0.1700
Data Index: 6982136 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8482. Min Range: -11.8482
Max Act: 9.9732. Min Act: -0.1700
Data Index: 2493149 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8482. Min Range: -11.8482
Max Act: 9.9732. Min Act: -0.1700
Data Index: 366688 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8482. Min Range: -11.8482
Max Act: 9.9732. Min Act: -0.1700
Data Index: 3134834 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8482. Min Range: -11.8482
Max Act: 9.9107. Min Act: -0.1700
Data Index: 4346847 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8482. Min Range: -11.8482
Max Act: 9.9732. Min Act: -0.1700
Data Index: 5992766 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19