Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.5453. Min Act: -0.1700
Data Index: 4745990 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.3578. Min Act: -0.1700
Data Index: 4957352 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.3578. Min Act: -0.1700
Data Index: 6904337 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.2953. Min Act: -0.1700
Data Index: 8114647 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.1703. Min Act: -0.1700
Data Index: 1319845 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.1703. Min Act: -0.1700
Data Index: 6918514 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.1078. Min Act: -0.1700
Data Index: 7489295 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.1078. Min Act: -0.1700
Data Index: 8142914 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.1078. Min Act: -0.1700
Data Index: 4917327 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5453. Min Range: -9.5453
Max Act: 9.1078. Min Act: -0.1700
Data Index: 4607057 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.9203. Min Act: -0.1700
Data Index: 7873227 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.9828. Min Act: -0.1700
Data Index: 8214409 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.9203. Min Act: -0.1700
Data Index: 7148593 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.9203. Min Act: -0.1700
Data Index: 2780282 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.8578. Min Act: -0.1700
Data Index: 7444067 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.7953. Min Act: -0.1700
Data Index: 8416472 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.7953. Min Act: -0.1700
Data Index: 376330 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.7953. Min Act: -0.1700
Data Index: 8802681 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.7328. Min Act: -0.1700
Data Index: 6129561 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5453. Min Range: -9.5453
Max Act: 8.7328. Min Act: -0.1700
Data Index: 7025303 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19