Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3178. Min Range: -5.3178
Max Act: 5.3178. Min Act: -0.1700
Data Index: 4807398 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3178. Min Range: -5.3178
Max Act: 5.0991. Min Act: -0.1700
Data Index: 4106679 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3178. Min Range: -5.3178
Max Act: 5.0678. Min Act: -0.1700
Data Index: 7768573 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3178. Min Range: -5.3178
Max Act: 5.0678. Min Act: -0.1700
Data Index: 7318679 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3178. Min Range: -5.3178
Max Act: 5.0366. Min Act: -0.1700
Data Index: 5918515 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3178. Min Range: -5.3178
Max Act: 5.0678. Min Act: -0.1700
Data Index: 5747539 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3178. Min Range: -5.3178
Max Act: 5.0053. Min Act: -0.1700
Data Index: 838684 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.9428. Min Act: -0.1700
Data Index: 1508255 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.9428. Min Act: -0.1700
Data Index: 5747512 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.9116. Min Act: -0.1700
Data Index: 8231555 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.9116. Min Act: -0.1700
Data Index: 6238123 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.9116. Min Act: -0.1700
Data Index: 134183 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.9116. Min Act: -0.1700
Data Index: 5151112 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.8803. Min Act: -0.1700
Data Index: 602211 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.8803. Min Act: -0.1700
Data Index: 2440989 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.8803. Min Act: -0.1700
Data Index: 3621323 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.8491. Min Act: -0.1700
Data Index: 6926619 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.8491. Min Act: -0.1700
Data Index: 7555980 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.8491. Min Act: -0.1700
Data Index: 7369421 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3178. Min Range: -5.3178
Max Act: 4.8491. Min Act: -0.1700
Data Index: 5093880 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19