Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1056. Min Range: -8.1056
Max Act: 8.1056. Min Act: -0.1700
Data Index: 429383 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.8244. Min Act: -0.1700
Data Index: 877006 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.6681. Min Act: -0.1700
Data Index: 3628477 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.6056. Min Act: -0.1700
Data Index: 1029889 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.5744. Min Act: -0.1700
Data Index: 3828354 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.6056. Min Act: -0.1700
Data Index: 5867812 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.5744. Min Act: -0.1700
Data Index: 15441 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.5431. Min Act: -0.1700
Data Index: 2550579 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.5431. Min Act: -0.1700
Data Index: 3727894 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4494. Min Act: -0.1700
Data Index: 4778649 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4806. Min Act: -0.1700
Data Index: 1181295 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.5119. Min Act: -0.1700
Data Index: 263554 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4806. Min Act: -0.1700
Data Index: 7223798 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4806. Min Act: -0.1700
Data Index: 293648 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4806. Min Act: -0.1700
Data Index: 3591222 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4806. Min Act: -0.1700
Data Index: 7647531 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4806. Min Act: -0.1700
Data Index: 4851901 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4806. Min Act: -0.1700
Data Index: 5524984 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4181. Min Act: -0.1700
Data Index: 661989 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1056. Min Range: -8.1056
Max Act: 7.4494. Min Act: -0.1700
Data Index: 5667391 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19