Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.9375. Min Act: -0.1700
Data Index: 1899879 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.9062. Min Act: -0.1700
Data Index: 1248569 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.8437. Min Act: -0.1700
Data Index: 4348971 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.8437. Min Act: -0.1700
Data Index: 38071 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.8125. Min Act: -0.1700
Data Index: 618826 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7812. Min Act: -0.1700
Data Index: 2078405 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7812. Min Act: -0.1700
Data Index: 1059533 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7187. Min Act: -0.1700
Data Index: 3276869 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7187. Min Act: -0.1700
Data Index: 1726610 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7187. Min Act: -0.1700
Data Index: 5312730 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7187. Min Act: -0.1700
Data Index: 5705964 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7187. Min Act: -0.1700
Data Index: 6896451 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.7187. Min Act: -0.1700
Data Index: 3026056 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.6562. Min Act: -0.1700
Data Index: 3566341 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.6875. Min Act: -0.1700
Data Index: 4330986 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.6562. Min Act: -0.1700
Data Index: 8757311 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.6875. Min Act: -0.1700
Data Index: 5961806 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.6562. Min Act: -0.1700
Data Index: 7008534 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.6562. Min Act: -0.1700
Data Index: 633085 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9375. Min Range: -6.9375
Max Act: 6.6250. Min Act: -0.1700
Data Index: 6593930 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19