Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.9027. Min Act: -0.1700
Data Index: 936432 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.8090. Min Act: -0.1700
Data Index: 6662352 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.7152. Min Act: -0.1700
Data Index: 6302361 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6840. Min Act: -0.1700
Data Index: 1995890 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6527. Min Act: -0.1700
Data Index: 7342431 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6215. Min Act: -0.1700
Data Index: 1815211 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.6215. Min Act: -0.1698
Data Index: 193063 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5902. Min Act: -0.1700
Data Index: 7021178 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5902. Min Act: -0.1700
Data Index: 7565537 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5590. Min Act: -0.1700
Data Index: 1798445 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5590. Min Act: -0.1700
Data Index: 1958061 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5590. Min Act: -0.1700
Data Index: 5632122 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5277. Min Act: -0.1700
Data Index: 2404761 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5277. Min Act: -0.1700
Data Index: 4738167 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5277. Min Act: -0.1700
Data Index: 5726061 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5277. Min Act: -0.1700
Data Index: 694540 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.4965. Min Act: -0.1700
Data Index: 4249041 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5277. Min Act: -0.1700
Data Index: 2020668 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5277. Min Act: -0.1700
Data Index: 4777312 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9027. Min Range: -4.9027
Max Act: 4.5277. Min Act: -0.1700
Data Index: 7052146 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19