Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1874 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4692. Min Range: -7.4692
Max Act: 7.4692. Min Act: -0.1700
Data Index: 7321908 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4692. Min Range: -7.4692
Max Act: 7.2817. Min Act: -0.1700
Data Index: 2499366 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4692. Min Range: -7.4692
Max Act: 7.1880. Min Act: -0.1700
Data Index: 3559062 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4692. Min Range: -7.4692
Max Act: 7.1567. Min Act: -0.1700
Data Index: 2807153 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4692. Min Range: -7.4692
Max Act: 7.1880. Min Act: -0.1700
Data Index: 3028501 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4692. Min Range: -7.4692
Max Act: 7.0317. Min Act: -0.1700
Data Index: 3888503 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4692. Min Range: -7.4692
Max Act: 7.0005. Min Act: -0.1700
Data Index: 8466077 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9692. Min Act: -0.1700
Data Index: 991116 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9692. Min Act: -0.1700
Data Index: 6085581 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9380. Min Act: -0.1700
Data Index: 3076260 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9380. Min Act: -0.1700
Data Index: 5219310 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9380. Min Act: -0.1700
Data Index: 8426856 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9380. Min Act: -0.1700
Data Index: 4571206 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9067. Min Act: -0.1700
Data Index: 1732030 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.9380. Min Act: -0.1700
Data Index: 5540114 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.8755. Min Act: -0.1700
Data Index: 2521190 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.8755. Min Act: -0.1700
Data Index: 3831558 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.8755. Min Act: -0.1700
Data Index: 4521106 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.8755. Min Act: -0.1700
Data Index: 408343 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4692. Min Range: -7.4692
Max Act: 6.8755. Min Act: -0.1700
Data Index: 3520213 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19