Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4317. Min Range: -6.4317
Max Act: 6.4317. Min Act: -0.1700
Data Index: 8716392 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4317. Min Range: -6.4317
Max Act: 6.0879. Min Act: -0.1700
Data Index: 6283097 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4317. Min Range: -6.4317
Max Act: 6.0567. Min Act: -0.1700
Data Index: 5067887 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4317. Min Range: -6.4317
Max Act: 6.0254. Min Act: -0.1700
Data Index: 7982187 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.9942. Min Act: -0.1700
Data Index: 8607984 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.9942. Min Act: -0.1700
Data Index: 4941613 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.9629. Min Act: -0.1700
Data Index: 4151470 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.9629. Min Act: -0.1700
Data Index: 7444748 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.9629. Min Act: -0.1700
Data Index: 1530788 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.9004. Min Act: -0.1700
Data Index: 4079417 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.9004. Min Act: -0.1700
Data Index: 5912339 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.8692. Min Act: -0.1700
Data Index: 1246429 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.8379. Min Act: -0.1700
Data Index: 8626926 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.8067. Min Act: -0.1700
Data Index: 3914857 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.8067. Min Act: -0.1700
Data Index: 5646518 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.8067. Min Act: -0.1700
Data Index: 2825387 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.7754. Min Act: -0.1700
Data Index: 4174786 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.7754. Min Act: -0.1700
Data Index: 5603344 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.7754. Min Act: -0.1700
Data Index: 7543936 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4317. Min Range: -6.4317
Max Act: 5.7442. Min Act: -0.1700
Data Index: 63126 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19