Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5079 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.7060. Min Range: -14.7060
Max Act: 14.7060. Min Act: -0.1700
Data Index: 3540728 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.7060. Min Range: -14.7060
Max Act: 14.2685. Min Act: -0.1700
Data Index: 8594637 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.7060. Min Range: -14.7060
Max Act: 14.1435. Min Act: -0.1700
Data Index: 7593499 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.7060. Min Range: -14.7060
Max Act: 14.0185. Min Act: -0.1700
Data Index: 1450566 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.7060. Min Range: -14.7060
Max Act: 14.0810. Min Act: -0.1700
Data Index: 904102 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.9560. Min Act: -0.1700
Data Index: 3469754 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.9560. Min Act: -0.1700
Data Index: 1290859 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 4098799 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 5126119 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 5964221 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 1547520 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 2463117 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 6735891 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 3594270 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8935. Min Act: -0.1700
Data Index: 3126339 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8310. Min Act: -0.1700
Data Index: 587249 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8310. Min Act: -0.1700
Data Index: 1954270 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8310. Min Act: -0.1700
Data Index: 7625661 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.8310. Min Act: -0.1700
Data Index: 3529232 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.7060. Min Range: -14.7060
Max Act: 13.7685. Min Act: -0.1700
Data Index: 5678364 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19