Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.5767. Min Act: -0.1700
Data Index: 6562616 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.4204. Min Act: -0.1700
Data Index: 3219168 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.3579. Min Act: -0.1700
Data Index: 2858979 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.2954. Min Act: -0.1700
Data Index: 2484990 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.2642. Min Act: -0.1700
Data Index: 5543283 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.1704. Min Act: -0.1700
Data Index: 7549163 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.1392. Min Act: -0.1700
Data Index: 176892 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.1079. Min Act: -0.1700
Data Index: 7929653 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.1079. Min Act: -0.1700
Data Index: 2109771 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.0454. Min Act: -0.1700
Data Index: 7918327 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.0767. Min Act: -0.1700
Data Index: 3988969 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.0142. Min Act: -0.1700
Data Index: 842372 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5767. Min Range: -6.5767
Max Act: 5.9829. Min Act: -0.1700
Data Index: 887612 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.0142. Min Act: -0.1700
Data Index: 6809788 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.0142. Min Act: -0.1700
Data Index: 8292079 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.0454. Min Act: -0.1700
Data Index: 4732431 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5767. Min Range: -6.5767
Max Act: 5.9829. Min Act: -0.1700
Data Index: 7881338 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5767. Min Range: -6.5767
Max Act: 6.0142. Min Act: -0.1700
Data Index: 4051173 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5767. Min Range: -6.5767
Max Act: 5.9829. Min Act: -0.1700
Data Index: 5480143 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5767. Min Range: -6.5767
Max Act: 5.9517. Min Act: -0.1700
Data Index: 7885051 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19