Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1351 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.9265. Min Act: -0.1700
Data Index: 3630904 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7702. Min Act: -0.1700
Data Index: 6087553 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7390. Min Act: -0.1700
Data Index: 6484517 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7390. Min Act: -0.1700
Data Index: 2267715 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7390. Min Act: -0.1700
Data Index: 4455600 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7390. Min Act: -0.1700
Data Index: 4569860 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7077. Min Act: -0.1700
Data Index: 7206108 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7390. Min Act: -0.1700
Data Index: 7018195 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.7077. Min Act: -0.1700
Data Index: 4790586 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.6765. Min Act: -0.1700
Data Index: 199624 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.6765. Min Act: -0.1700
Data Index: 5198168 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.6452. Min Act: -0.1700
Data Index: 2174182 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.6140. Min Act: -0.1698
Data Index: 2126742 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.6140. Min Act: -0.1700
Data Index: 8577046 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.5827. Min Act: -0.1700
Data Index: 841898 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.6140. Min Act: -0.1700
Data Index: 3323635 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.5827. Min Act: -0.1700
Data Index: 6104577 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.5827. Min Act: -0.1700
Data Index: 6389635 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.5827. Min Act: -0.1700
Data Index: 2654195 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9265. Min Range: -5.9265
Max Act: 5.5827. Min Act: -0.1700
Data Index: 981145 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19