Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 721 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.5652. Min Act: -0.1700
Data Index: 2471789 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.2840. Min Act: -0.1700
Data Index: 3138695 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.2527. Min Act: -0.1700
Data Index: 7894293 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.2527. Min Act: -0.1700
Data Index: 5355683 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.2215. Min Act: -0.1700
Data Index: 3417541 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.1902. Min Act: -0.1700
Data Index: 2480006 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.1902. Min Act: -0.1700
Data Index: 5964686 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.1590. Min Act: -0.1700
Data Index: 5458702 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.0965. Min Act: -0.1700
Data Index: 8636537 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.0652. Min Act: -0.1700
Data Index: 7513614 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.0652. Min Act: -0.1700
Data Index: 8062454 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.0652. Min Act: -0.1700
Data Index: 3520196 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.0652. Min Act: -0.1700
Data Index: 5272374 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5652. Min Range: -5.5652
Max Act: 5.0027. Min Act: -0.1700
Data Index: 1607506 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5652. Min Range: -5.5652
Max Act: 4.9715. Min Act: -0.1700
Data Index: 4069918 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5652. Min Range: -5.5652
Max Act: 4.9715. Min Act: -0.1700
Data Index: 3576756 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5652. Min Range: -5.5652
Max Act: 4.9402. Min Act: -0.1700
Data Index: 3030109 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5652. Min Range: -5.5652
Max Act: 4.9402. Min Act: -0.1700
Data Index: 8442903 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5652. Min Range: -5.5652
Max Act: 4.9402. Min Act: -0.1700
Data Index: 99376 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5652. Min Range: -5.5652
Max Act: 4.9090. Min Act: -0.1700
Data Index: 7248592 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19