Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1690. Min Range: -10.1690
Max Act: 10.1690. Min Act: -0.1700
Data Index: 7571106 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.7315. Min Act: -0.1700
Data Index: 6166097 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.5440. Min Act: -0.1700
Data Index: 2458469 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.3565. Min Act: -0.1700
Data Index: 7726163 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.2940. Min Act: -0.1700
Data Index: 4286698 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.1065. Min Act: -0.1700
Data Index: 8024445 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.0440. Min Act: -0.1700
Data Index: 1113677 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.0440. Min Act: -0.1700
Data Index: 5167673 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.0440. Min Act: -0.1700
Data Index: 4837229 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.9815. Min Act: -0.1700
Data Index: 5937868 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1690. Min Range: -10.1690
Max Act: 9.0440. Min Act: -0.1700
Data Index: 8809412 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.9815. Min Act: -0.1700
Data Index: 5305872 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.9190. Min Act: -0.1700
Data Index: 8169511 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.9190. Min Act: -0.1700
Data Index: 5148857 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.9190. Min Act: -0.1700
Data Index: 728779 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.9190. Min Act: -0.1700
Data Index: 7885538 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.8565. Min Act: -0.1700
Data Index: 8670091 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.8565. Min Act: -0.1700
Data Index: 551791 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.7940. Min Act: -0.1700
Data Index: 6494202 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1690. Min Range: -10.1690
Max Act: 8.7940. Min Act: -0.1700
Data Index: 8326970 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19