Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2703. Min Range: -8.2703
Max Act: 8.2703. Min Act: -0.1661
Data Index: 4776054 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2703. Min Range: -8.2703
Max Act: 8.0828. Min Act: -0.1700
Data Index: 267167 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2703. Min Range: -8.2703
Max Act: 8.0516. Min Act: -0.1700
Data Index: 5859808 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.7391. Min Act: -0.1700
Data Index: 50976 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.7078. Min Act: -0.1521
Data Index: 87156 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.6766. Min Act: -0.1700
Data Index: 5728286 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.6453. Min Act: -0.1558
Data Index: 2686531 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.6141. Min Act: -0.1700
Data Index: 7743225 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.5516. Min Act: -0.1697
Data Index: 8334922 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.5516. Min Act: -0.1698
Data Index: 267168 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.5516. Min Act: -0.1700
Data Index: 7006302 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.5203. Min Act: -0.1700
Data Index: 1490469 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.5203. Min Act: -0.1698
Data Index: 7170779 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.5516. Min Act: -0.1643
Data Index: 5181056 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.4578. Min Act: -0.1682
Data Index: 7170780 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.4266. Min Act: -0.1700
Data Index: 578893 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.4266. Min Act: -0.1700
Data Index: 4733232 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.4266. Min Act: -0.1699
Data Index: 2772712 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.4266. Min Act: -0.1699
Data Index: 2164913 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2703. Min Range: -8.2703
Max Act: 7.3328. Min Act: -0.1700
Data Index: 7420907 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19