Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4961 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1821. Min Range: -8.1821
Max Act: 8.1821. Min Act: -0.1700
Data Index: 3357561 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.9946. Min Act: -0.1700
Data Index: 5037802 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.9321. Min Act: -0.1700
Data Index: 6654822 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.8071. Min Act: -0.1700
Data Index: 3060917 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.7446. Min Act: -0.1700
Data Index: 937570 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.6821. Min Act: -0.1700
Data Index: 6901436 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.6821. Min Act: -0.1700
Data Index: 5549777 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.5884. Min Act: -0.1700
Data Index: 4382250 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.6196. Min Act: -0.1700
Data Index: 3614016 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.5884. Min Act: -0.1700
Data Index: 4764434 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.5259. Min Act: -0.1700
Data Index: 1852819 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.5259. Min Act: -0.1700
Data Index: 1061356 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.5259. Min Act: -0.1700
Data Index: 2529358 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.4634. Min Act: -0.1700
Data Index: 2566763 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.4321. Min Act: -0.1700
Data Index: 6447120 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.4321. Min Act: -0.1700
Data Index: 1394606 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.4009. Min Act: -0.1700
Data Index: 3045981 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.3696. Min Act: -0.1700
Data Index: 7340354 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.3696. Min Act: -0.1700
Data Index: 4714457 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1821. Min Range: -8.1821
Max Act: 7.3696. Min Act: -0.1700
Data Index: 7064083 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19