Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4498 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.6513. Min Act: -0.1700
Data Index: 6583712 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.4325. Min Act: -0.1700
Data Index: 4077814 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.3075. Min Act: -0.1700
Data Index: 6605973 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.2763. Min Act: -0.1700
Data Index: 1583089 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.2763. Min Act: -0.1700
Data Index: 6860863 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.2450. Min Act: -0.1700
Data Index: 4676819 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.2138. Min Act: -0.1700
Data Index: 7952757 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1825. Min Act: -0.1700
Data Index: 8182739 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1513. Min Act: -0.1700
Data Index: 3947073 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1513. Min Act: -0.1700
Data Index: 3895121 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1513. Min Act: -0.1700
Data Index: 2338089 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1513. Min Act: -0.1700
Data Index: 7742672 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1513. Min Act: -0.1700
Data Index: 5273306 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1200. Min Act: -0.1700
Data Index: 2185378 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1200. Min Act: -0.1700
Data Index: 2576649 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1200. Min Act: -0.1700
Data Index: 1371147 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.1200. Min Act: -0.1700
Data Index: 865748 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.0888. Min Act: -0.1700
Data Index: 7660468 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.0888. Min Act: -0.1700
Data Index: 3904301 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6513. Min Range: -5.6513
Max Act: 5.0888. Min Act: -0.1700
Data Index: 4142812 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19