Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4855 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.8512. Min Act: -0.1700
Data Index: 5269722 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.7574. Min Act: -0.1700
Data Index: 2424659 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.6949. Min Act: -0.1700
Data Index: 5709312 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.6949. Min Act: -0.1700
Data Index: 3616046 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.6012. Min Act: -0.1700
Data Index: 4964813 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.6637. Min Act: -0.1700
Data Index: 6803508 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.6012. Min Act: -0.1700
Data Index: 3831131 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.6012. Min Act: -0.1700
Data Index: 4928219 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.6012. Min Act: -0.1700
Data Index: 3000608 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5699. Min Act: -0.1700
Data Index: 1217546 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5387. Min Act: -0.1700
Data Index: 3519576 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5387. Min Act: -0.1700
Data Index: 2724798 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5387. Min Act: -0.1700
Data Index: 2516426 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5074. Min Act: -0.1700
Data Index: 8701818 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5387. Min Act: -0.1700
Data Index: 5209310 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5074. Min Act: -0.1700
Data Index: 5874571 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.5074. Min Act: -0.1700
Data Index: 7878814 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.4762. Min Act: -0.1700
Data Index: 4293044 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.4762. Min Act: -0.1700
Data Index: 7791984 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8512. Min Range: -5.8512
Max Act: 5.4449. Min Act: -0.1700
Data Index: 2773451 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19