Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9866. Min Act: -0.1699
Data Index: 5069545 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9357. Min Act: -0.1700
Data Index: 3194448 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9187. Min Act: -0.1700
Data Index: 1139047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9527. Min Act: -0.1700
Data Index: 5047434 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9187. Min Act: -0.1700
Data Index: 1840796 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9187. Min Act: -0.1699
Data Index: 3401843 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9187. Min Act: -0.1700
Data Index: 5075261 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9017. Min Act: -0.1699
Data Index: 2844238 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9187. Min Act: -0.1700
Data Index: 3266440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.9017. Min Act: -0.1697
Data Index: 8457231 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8846. Min Act: -0.1700
Data Index: 1851441 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8675. Min Act: -0.1688
Data Index: 8731858 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8846. Min Act: -0.1700
Data Index: 4861515 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8846. Min Act: -0.1700
Data Index: 8381620 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8846. Min Act: -0.1700
Data Index: 3350158 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8675. Min Act: -0.1700
Data Index: 2830985 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8333. Min Act: -0.1700
Data Index: 4464923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8504. Min Act: -0.1693
Data Index: 2415713 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8675. Min Act: -0.1694
Data Index: 6696098 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9866. Min Range: -1.9866
Max Act: 1.8504. Min Act: -0.1694
Data Index: 6389390 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19