Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5988 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1875. Min Range: -5.1875
Max Act: 5.1875. Min Act: -0.1700
Data Index: 1205524 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1875. Min Range: -5.1875
Max Act: 5.0937. Min Act: -0.1700
Data Index: 8291727 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1875. Min Range: -5.1875
Max Act: 5.0625. Min Act: -0.1700
Data Index: 7877285 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1875. Min Range: -5.1875
Max Act: 5.0312. Min Act: -0.1700
Data Index: 1278501 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1875. Min Range: -5.1875
Max Act: 5.0000. Min Act: -0.1700
Data Index: 8258840 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.9062. Min Act: -0.1700
Data Index: 676913 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.9062. Min Act: -0.1700
Data Index: 7219565 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.9062. Min Act: -0.1700
Data Index: 2581998 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.8437. Min Act: -0.1700
Data Index: 2049627 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.8437. Min Act: -0.1700
Data Index: 8755913 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.8125. Min Act: -0.1700
Data Index: 1373614 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7812. Min Act: -0.1700
Data Index: 8616303 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7812. Min Act: -0.1700
Data Index: 7157592 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7812. Min Act: -0.1700
Data Index: 5942090 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7812. Min Act: -0.1700
Data Index: 1572538 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7500. Min Act: -0.1700
Data Index: 8291744 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7500. Min Act: -0.1700
Data Index: 976252 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7500. Min Act: -0.1700
Data Index: 4439828 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7812. Min Act: -0.1700
Data Index: 1734554 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1875. Min Range: -5.1875
Max Act: 4.7500. Min Act: -0.1700
Data Index: 1278502 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19