Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1844 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.6631. Min Act: -0.1700
Data Index: 7727747 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.6631. Min Act: -0.1700
Data Index: 6159535 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.5381. Min Act: -0.1700
Data Index: 6472225 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.3506. Min Act: -0.1700
Data Index: 8315553 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.3506. Min Act: -0.1700
Data Index: 2862511 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.3506. Min Act: -0.1700
Data Index: 6020074 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.2256. Min Act: -0.1700
Data Index: 7755025 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.2256. Min Act: -0.1700
Data Index: 3873047 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.2256. Min Act: -0.1700
Data Index: 837805 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.1631. Min Act: -0.1700
Data Index: 1412800 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.1631. Min Act: -0.1700
Data Index: 6237639 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.1631. Min Act: -0.1700
Data Index: 4268213 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.1631. Min Act: -0.1700
Data Index: 3445792 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.0381. Min Act: -0.1700
Data Index: 2418907 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.1006. Min Act: -0.1700
Data Index: 3770550 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.1006. Min Act: -0.1700
Data Index: 685882 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.1006. Min Act: -0.1700
Data Index: 3030354 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.0381. Min Act: -0.1700
Data Index: 4140369 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.0381. Min Act: -0.1700
Data Index: 6779351 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6631. Min Range: -8.6631
Max Act: 8.0381. Min Act: -0.1700
Data Index: 1615048 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19