Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 752 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.8922. Min Act: -0.1700
Data Index: 1755897 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.8922. Min Act: -0.1700
Data Index: 7878368 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.8922. Min Act: -0.1700
Data Index: 5267398 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7047. Min Act: -0.1700
Data Index: 7619595 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7672. Min Act: -0.1700
Data Index: 8033687 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7672. Min Act: -0.1700
Data Index: 2895023 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7672. Min Act: -0.1700
Data Index: 7620499 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7047. Min Act: -0.1700
Data Index: 2913731 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7047. Min Act: -0.1700
Data Index: 4973993 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7047. Min Act: -0.1700
Data Index: 7231075 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7047. Min Act: -0.1700
Data Index: 2885462 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.7672. Min Act: -0.1700
Data Index: 7650029 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.6422. Min Act: -0.1700
Data Index: 5113034 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.5797. Min Act: -0.1700
Data Index: 1997917 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.6422. Min Act: -0.1700
Data Index: 1023514 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.5797. Min Act: -0.1700
Data Index: 2202342 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.5797. Min Act: -0.1700
Data Index: 4980913 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.5797. Min Act: -0.1700
Data Index: 4149456 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.5797. Min Act: -0.1700
Data Index: 7819188 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8922. Min Range: -7.8922
Max Act: 7.5172. Min Act: -0.1700
Data Index: 330566 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19