Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.2791. Min Act: -0.1700
Data Index: 7093998 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.1853. Min Act: -0.1700
Data Index: 2976929 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.1228. Min Act: -0.1700
Data Index: 5014010 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0915. Min Act: -0.1700
Data Index: 5315010 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0915. Min Act: -0.1700
Data Index: 6154411 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0603. Min Act: -0.1700
Data Index: 989966 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0915. Min Act: -0.1700
Data Index: 701453 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0603. Min Act: -0.1700
Data Index: 7232691 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0603. Min Act: -0.1700
Data Index: 7269080 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0603. Min Act: -0.1700
Data Index: 4667736 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0603. Min Act: -0.1700
Data Index: 4069831 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2791. Min Range: -4.2791
Max Act: 3.9978. Min Act: -0.1700
Data Index: 1406521 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0290. Min Act: -0.1700
Data Index: 5289158 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0290. Min Act: -0.1700
Data Index: 6506933 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0290. Min Act: -0.1700
Data Index: 2863483 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0603. Min Act: -0.1700
Data Index: 701452 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0290. Min Act: -0.1700
Data Index: 2577775 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0290. Min Act: -0.1700
Data Index: 6020868 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2791. Min Range: -4.2791
Max Act: 4.0290. Min Act: -0.1700
Data Index: 693749 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2791. Min Range: -4.2791
Max Act: 3.9978. Min Act: -0.1700
Data Index: 454828 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19