Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0374. Min Range: -6.0374
Max Act: 6.0374. Min Act: -0.1700
Data Index: 6367651 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.9124. Min Act: -0.1700
Data Index: 5920411 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.8812. Min Act: -0.1700
Data Index: 5261621 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.8499. Min Act: -0.1700
Data Index: 1650837 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.8499. Min Act: -0.1700
Data Index: 7172093 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.8499. Min Act: -0.1700
Data Index: 756365 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.8187. Min Act: -0.1700
Data Index: 636970 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7874. Min Act: -0.1700
Data Index: 7281296 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7874. Min Act: -0.1700
Data Index: 523597 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7562. Min Act: -0.1700
Data Index: 7184137 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7562. Min Act: -0.1700
Data Index: 680821 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7562. Min Act: -0.1700
Data Index: 5130729 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7562. Min Act: -0.1700
Data Index: 5750048 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7874. Min Act: -0.1700
Data Index: 1564435 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7562. Min Act: -0.1700
Data Index: 6032668 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7249. Min Act: -0.1700
Data Index: 6126559 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7249. Min Act: -0.1700
Data Index: 563310 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7249. Min Act: -0.1700
Data Index: 3168605 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7249. Min Act: -0.1700
Data Index: 5826717 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0374. Min Range: -6.0374
Max Act: 5.7249. Min Act: -0.1700
Data Index: 2409838 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19