Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5096. Min Range: -8.5096
Max Act: 8.5096. Min Act: -0.1700
Data Index: 8414063 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5096. Min Range: -8.5096
Max Act: 8.0096. Min Act: -0.1700
Data Index: 7683182 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.8533. Min Act: -0.1700
Data Index: 3497080 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.7908. Min Act: -0.1700
Data Index: 7683181 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.6658. Min Act: -0.1700
Data Index: 4117931 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.6971. Min Act: -0.1700
Data Index: 395642 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.5721. Min Act: -0.1700
Data Index: 5957651 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.5096. Min Act: -0.1700
Data Index: 8570365 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.5096. Min Act: -0.1700
Data Index: 7039947 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.4783. Min Act: -0.1700
Data Index: 1526206 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.4783. Min Act: -0.1700
Data Index: 8403478 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.4783. Min Act: -0.1700
Data Index: 2499980 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.4471. Min Act: -0.1700
Data Index: 1038507 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.3846. Min Act: -0.1700
Data Index: 2822294 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.3846. Min Act: -0.1700
Data Index: 5780416 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.3846. Min Act: -0.1700
Data Index: 4848794 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.3846. Min Act: -0.1700
Data Index: 3497083 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.3846. Min Act: -0.1700
Data Index: 1806923 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.3533. Min Act: -0.1700
Data Index: 7570150 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5096. Min Range: -8.5096
Max Act: 7.3221. Min Act: -0.1700
Data Index: 6217610 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19