Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2074 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.9390. Min Act: -0.1700
Data Index: 8614286 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.9231. Min Act: -0.1700
Data Index: 7405322 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8914. Min Act: -0.1700
Data Index: 4621199 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8914. Min Act: -0.1700
Data Index: 4954470 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8597. Min Act: -0.1700
Data Index: 7405323 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8597. Min Act: -0.1700
Data Index: 3978301 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8438. Min Act: -0.1700
Data Index: 3458380 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8438. Min Act: -0.1700
Data Index: 5844459 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8279. Min Act: -0.1700
Data Index: 607855 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8279. Min Act: -0.1700
Data Index: 3800042 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8438. Min Act: -0.1700
Data Index: 7818464 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8279. Min Act: -0.1700
Data Index: 640710 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8120. Min Act: -0.1700
Data Index: 2196170 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8279. Min Act: -0.1700
Data Index: 5200143 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8120. Min Act: -0.1700
Data Index: 7405331 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8120. Min Act: -0.1700
Data Index: 7039837 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8120. Min Act: -0.1700
Data Index: 1038574 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8120. Min Act: -0.1700
Data Index: 1825798 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8120. Min Act: -0.1700
Data Index: 1773329 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9390. Min Range: -2.9390
Max Act: 2.8120. Min Act: -0.1700
Data Index: 4804242 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19