Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.7468. Min Act: -0.1700
Data Index: 652546 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.7468. Min Act: -0.1700
Data Index: 7589074 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6843. Min Act: -0.1700
Data Index: 5319433 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6843. Min Act: -0.1700
Data Index: 1308702 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6843. Min Act: -0.1700
Data Index: 8266192 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 15393 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 6925010 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 5414769 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 1789461 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 5229257 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 3387660 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 4794103 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 7940735 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 6980065 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 4121882 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.5593. Min Act: -0.1700
Data Index: 120381 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.5593. Min Act: -0.1700
Data Index: 1358633 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.5593. Min Act: -0.1700
Data Index: 3519733 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.4968. Min Act: -0.1700
Data Index: 3527717 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7468. Min Range: -7.7468
Max Act: 7.5593. Min Act: -0.1700
Data Index: 5948163 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19