Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.6029. Min Act: -0.1700
Data Index: 862397 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.4154. Min Act: -0.1700
Data Index: 7450971 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.3529. Min Act: -0.1700
Data Index: 863208 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.2904. Min Act: -0.1700
Data Index: 2462429 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.2279. Min Act: -0.1700
Data Index: 5987413 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.1654. Min Act: -0.1700
Data Index: 1073744 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.1654. Min Act: -0.1700
Data Index: 5364174 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.1029. Min Act: -0.1700
Data Index: 7796666 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6029. Min Range: -8.6029
Max Act: 8.1029. Min Act: -0.1700
Data Index: 8439003 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.9779. Min Act: -0.1700
Data Index: 603691 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.9779. Min Act: -0.1700
Data Index: 1532648 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.9154. Min Act: -0.1700
Data Index: 2471811 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.8529. Min Act: -0.1700
Data Index: 1986600 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 6058128 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 1711159 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.7279. Min Act: -0.1700
Data Index: 2054768 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 7489116 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 3792891 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 386159 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6029. Min Range: -8.6029
Max Act: 7.7904. Min Act: -0.1700
Data Index: 4805695 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19