Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 913 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.4499. Min Act: -0.1700
Data Index: 5243334 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.1374. Min Act: -0.1700
Data Index: 337693 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.1062. Min Act: -0.1700
Data Index: 3744500 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0749. Min Act: -0.1700
Data Index: 4777887 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0749. Min Act: -0.1700
Data Index: 7892816 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0436. Min Act: -0.1700
Data Index: 1396642 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0436. Min Act: -0.1700
Data Index: 301782 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0124. Min Act: -0.1700
Data Index: 5892534 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0124. Min Act: -0.1700
Data Index: 918962 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0124. Min Act: -0.1700
Data Index: 6168751 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9811. Min Act: -0.1700
Data Index: 829490 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9811. Min Act: -0.1700
Data Index: 4524721 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9811. Min Act: -0.1700
Data Index: 2752573 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4499. Min Range: -4.4499
Max Act: 4.0124. Min Act: -0.1700
Data Index: 1570911 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9811. Min Act: -0.1700
Data Index: 6942722 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9186. Min Act: -0.1700
Data Index: 196921 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9186. Min Act: -0.1700
Data Index: 4004121 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9499. Min Act: -0.1700
Data Index: 3051104 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9186. Min Act: -0.1700
Data Index: 5989010 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4499. Min Range: -4.4499
Max Act: 3.9186. Min Act: -0.1700
Data Index: 6870192 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19