Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5682 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.7873. Min Act: -0.1700
Data Index: 2372267 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.7248. Min Act: -0.1700
Data Index: 615546 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.5373. Min Act: -0.1700
Data Index: 1124957 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.4436. Min Act: -0.1700
Data Index: 2605520 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.4748. Min Act: -0.1700
Data Index: 1124956 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.4748. Min Act: -0.1700
Data Index: 6726503 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.4436. Min Act: -0.1700
Data Index: 4896257 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.3498. Min Act: -0.1700
Data Index: 6297973 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.3186. Min Act: -0.1700
Data Index: 1124964 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2873. Min Act: -0.1700
Data Index: 3907460 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2873. Min Act: -0.1700
Data Index: 4308547 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2873. Min Act: -0.1700
Data Index: 3907455 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2873. Min Act: -0.1700
Data Index: 1004891 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2873. Min Act: -0.1700
Data Index: 8032226 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2561. Min Act: -0.1700
Data Index: 8784222 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2248. Min Act: -0.1700
Data Index: 5851663 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2248. Min Act: -0.1700
Data Index: 5889723 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2561. Min Act: -0.1700
Data Index: 7147479 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.2248. Min Act: -0.1700
Data Index: 2413139 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7873. Min Range: -7.7873
Max Act: 7.1936. Min Act: -0.1700
Data Index: 5764283 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19