Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3412. Min Range: -8.3412
Max Act: 8.3412. Min Act: -0.1700
Data Index: 2882730 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3412. Min Range: -8.3412
Max Act: 8.2162. Min Act: -0.1700
Data Index: 2714140 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3412. Min Range: -8.3412
Max Act: 8.2162. Min Act: -0.1700
Data Index: 2645748 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3412. Min Range: -8.3412
Max Act: 8.0287. Min Act: -0.1700
Data Index: 5155832 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.7787. Min Act: -0.1700
Data Index: 879779 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.7787. Min Act: -0.1700
Data Index: 4892937 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.6537. Min Act: -0.1700
Data Index: 7785174 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.6537. Min Act: -0.1700
Data Index: 5155831 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.6537. Min Act: -0.1700
Data Index: 2098179 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.6537. Min Act: -0.1700
Data Index: 8363527 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.5287. Min Act: -0.1700
Data Index: 3965567 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.5912. Min Act: -0.1700
Data Index: 7546141 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.4662. Min Act: -0.1700
Data Index: 5275034 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.4349. Min Act: -0.1700
Data Index: 6200590 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.4349. Min Act: -0.1700
Data Index: 5574443 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.4037. Min Act: -0.1700
Data Index: 5400179 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.3724. Min Act: -0.1700
Data Index: 4683730 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.3099. Min Act: -0.1700
Data Index: 7624848 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.3412. Min Act: -0.1700
Data Index: 5935529 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3412. Min Range: -8.3412
Max Act: 7.2787. Min Act: -0.1700
Data Index: 2882082 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19