Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0042. Min Range: -5.0042
Max Act: 5.0042. Min Act: -0.1700
Data Index: 6303077 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.9417. Min Act: -0.1700
Data Index: 7483037 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.9104. Min Act: -0.1700
Data Index: 7770186 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.8479. Min Act: -0.1700
Data Index: 21442 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.7542. Min Act: -0.1700
Data Index: 1858536 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6917. Min Act: -0.1700
Data Index: 75452 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6917. Min Act: -0.1700
Data Index: 8614180 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6917. Min Act: -0.1700
Data Index: 1011064 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6917. Min Act: -0.1700
Data Index: 7459626 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6917. Min Act: -0.1700
Data Index: 8700789 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6604. Min Act: -0.1700
Data Index: 3024343 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6604. Min Act: -0.1700
Data Index: 8081304 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6604. Min Act: -0.1700
Data Index: 5047236 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8419939 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6292. Min Act: -0.1700
Data Index: 1641282 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6292. Min Act: -0.1700
Data Index: 7497568 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.6292. Min Act: -0.1700
Data Index: 8667059 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.5979. Min Act: -0.1700
Data Index: 8087875 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.5979. Min Act: -0.1700
Data Index: 5268307 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0042. Min Range: -5.0042
Max Act: 4.5979. Min Act: -0.1700
Data Index: 6413688 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19