Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3903 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.7378. Min Act: -0.1700
Data Index: 8310741 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.7066. Min Act: -0.1700
Data Index: 7294317 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.5816. Min Act: -0.1700
Data Index: 6118805 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.5503. Min Act: -0.1700
Data Index: 8622013 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.5191. Min Act: -0.1700
Data Index: 5527311 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.4566. Min Act: -0.1700
Data Index: 8391046 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.4253. Min Act: -0.1700
Data Index: 8377963 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.3941. Min Act: -0.1700
Data Index: 8395738 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.3628. Min Act: -0.1700
Data Index: 7876941 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.3316. Min Act: -0.1700
Data Index: 7656242 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.2691. Min Act: -0.1700
Data Index: 631410 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.2691. Min Act: -0.1700
Data Index: 2952446 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.2378. Min Act: -0.1700
Data Index: 666909 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.2691. Min Act: -0.1700
Data Index: 8157046 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.2066. Min Act: -0.1700
Data Index: 4734835 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.2378. Min Act: -0.1700
Data Index: 5452875 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.1753. Min Act: -0.1700
Data Index: 2150221 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.2066. Min Act: -0.1700
Data Index: 19821 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.1441. Min Act: -0.1700
Data Index: 6485119 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7378. Min Range: -6.7378
Max Act: 6.1441. Min Act: -0.1700
Data Index: 5717310 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19