Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6157 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.8438. Min Act: -0.1700
Data Index: 4816660 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.6251. Min Act: -0.1700
Data Index: 2294314 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.3751. Min Act: -0.1700
Data Index: 8466707 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.3126. Min Act: -0.1700
Data Index: 1131102 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.3126. Min Act: -0.1700
Data Index: 4690830 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.2813. Min Act: -0.1700
Data Index: 5245811 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.2501. Min Act: -0.1700
Data Index: 8511111 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1876. Min Act: -0.1700
Data Index: 3671408 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1876. Min Act: -0.1700
Data Index: 912083 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1563. Min Act: -0.1700
Data Index: 8511112 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1563. Min Act: -0.1700
Data Index: 4152526 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1563. Min Act: -0.1700
Data Index: 581031 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 8111390 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 3262630 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 1797679 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.1251. Min Act: -0.1700
Data Index: 203740 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.0938. Min Act: -0.1700
Data Index: 6743372 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.0625. Min Act: -0.1700
Data Index: 3736187 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.0625. Min Act: -0.1700
Data Index: 5889344 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8438. Min Range: -4.8438
Max Act: 4.0625. Min Act: -0.1700
Data Index: 39804 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19