Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4382 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1707. Min Range: -4.1707
Max Act: 4.1707. Min Act: -0.1700
Data Index: 4160862 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1707. Min Range: -4.1707
Max Act: 4.0456. Min Act: -0.1700
Data Index: 5379500 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1707. Min Range: -4.1707
Max Act: 4.0144. Min Act: -0.1700
Data Index: 1435083 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.8893. Min Act: -0.1700
Data Index: 8549013 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.8268. Min Act: -0.1700
Data Index: 6740328 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.8581. Min Act: -0.1700
Data Index: 4919523 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.8268. Min Act: -0.1700
Data Index: 8806331 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7955. Min Act: -0.1700
Data Index: 1197787 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7642. Min Act: -0.1700
Data Index: 6480976 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7955. Min Act: -0.1700
Data Index: 6344002 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7955. Min Act: -0.1700
Data Index: 5471285 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7642. Min Act: -0.1700
Data Index: 7502236 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7330. Min Act: -0.1700
Data Index: 2027818 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7642. Min Act: -0.1700
Data Index: 3245259 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7330. Min Act: -0.1700
Data Index: 1780474 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7330. Min Act: -0.1700
Data Index: 7244183 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7330. Min Act: -0.1700
Data Index: 3160152 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7330. Min Act: -0.1700
Data Index: 3204831 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7017. Min Act: -0.1700
Data Index: 6612598 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1707. Min Range: -4.1707
Max Act: 3.7017. Min Act: -0.1700
Data Index: 3886097 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19