Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4466 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9387. Min Range: -8.9387
Max Act: 8.9387. Min Act: -0.1700
Data Index: 2731383 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9387. Min Range: -8.9387
Max Act: 8.5637. Min Act: -0.1700
Data Index: 8431828 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9387. Min Range: -8.9387
Max Act: 8.1887. Min Act: -0.1700
Data Index: 1547629 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.9387. Min Act: -0.1700
Data Index: 8130072 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.8762. Min Act: -0.1700
Data Index: 5451514 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.8137. Min Act: -0.1700
Data Index: 53021 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.7512. Min Act: -0.1700
Data Index: 476500 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.8137. Min Act: -0.1700
Data Index: 4038060 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.7512. Min Act: -0.1700
Data Index: 3103468 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.7512. Min Act: -0.1700
Data Index: 7438723 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6887. Min Act: -0.1700
Data Index: 5204822 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6887. Min Act: -0.1700
Data Index: 3369589 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6887. Min Act: -0.1700
Data Index: 8199103 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6887. Min Act: -0.1700
Data Index: 8363139 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6262. Min Act: -0.1700
Data Index: 2280921 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6262. Min Act: -0.1700
Data Index: 3506029 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.5637. Min Act: -0.1700
Data Index: 564817 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6887. Min Act: -0.1700
Data Index: 6658750 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6262. Min Act: -0.1700
Data Index: 3685272 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9387. Min Range: -8.9387
Max Act: 7.6262. Min Act: -0.1700
Data Index: 1717318 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19