Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4025 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 906422 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.8362. Min Act: -0.1700
Data Index: 2547532 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.8674. Min Act: -0.1700
Data Index: 5576345 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.8049. Min Act: -0.1700
Data Index: 8298074 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.8049. Min Act: -0.1700
Data Index: 7396561 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.7737. Min Act: -0.1700
Data Index: 751682 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.7424. Min Act: -0.1700
Data Index: 1291720 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.7424. Min Act: -0.1700
Data Index: 1111439 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6799. Min Act: -0.1700
Data Index: 3546604 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.7112. Min Act: -0.1700
Data Index: 6257028 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 5385827 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6799. Min Act: -0.1700
Data Index: 8038747 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6799. Min Act: -0.1700
Data Index: 2302912 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 2073159 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 4717296 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 7047528 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 7034832 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 1909664 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 956641 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8987. Min Range: -6.8987
Max Act: 6.6487. Min Act: -0.1700
Data Index: 4828711 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19