Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.8340. Min Act: -0.1700
Data Index: 7581494 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.7090. Min Act: -0.1700
Data Index: 3128715 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.6778. Min Act: -0.1700
Data Index: 3327494 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.6465. Min Act: -0.1700
Data Index: 5265914 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.5528. Min Act: -0.1700
Data Index: 2593116 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.5528. Min Act: -0.1700
Data Index: 1822843 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.5215. Min Act: -0.1700
Data Index: 6672752 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.4903. Min Act: -0.1700
Data Index: 4889664 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.4590. Min Act: -0.1700
Data Index: 6222510 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.4278. Min Act: -0.1700
Data Index: 6735580 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.3965. Min Act: -0.1700
Data Index: 7984047 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.3965. Min Act: -0.1700
Data Index: 1081540 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.3340. Min Act: -0.1700
Data Index: 31284 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.3028. Min Act: -0.1700
Data Index: 5792820 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.3028. Min Act: -0.1700
Data Index: 1616366 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.3028. Min Act: -0.1700
Data Index: 4085947 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.2715. Min Act: -0.1700
Data Index: 8003442 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.2715. Min Act: -0.1700
Data Index: 413711 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.2715. Min Act: -0.1700
Data Index: 6472205 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8340. Min Range: -5.8340
Max Act: 5.2715. Min Act: -0.1700
Data Index: 3893483 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19