Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2162 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.9902. Min Act: -0.1700
Data Index: 4368846 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.8339. Min Act: -0.1700
Data Index: 7870815 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.7557. Min Act: -0.1700
Data Index: 417357 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.7244. Min Act: -0.1700
Data Index: 5213317 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.6618. Min Act: -0.1700
Data Index: 3344109 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.6306. Min Act: -0.1700
Data Index: 2804653 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.6306. Min Act: -0.1700
Data Index: 4850809 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5993. Min Act: -0.1700
Data Index: 8245495 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5523. Min Act: -0.1700
Data Index: 3344414 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5836. Min Act: -0.1700
Data Index: 311777 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5679. Min Act: -0.1700
Data Index: 2884884 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5523. Min Act: -0.1700
Data Index: 683581 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5053. Min Act: -0.1700
Data Index: 4632617 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5366. Min Act: -0.1700
Data Index: 7486200 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5210. Min Act: -0.1700
Data Index: 3451736 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5053. Min Act: -0.1700
Data Index: 6628526 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.4896. Min Act: -0.1700
Data Index: 5375208 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.4896. Min Act: -0.1700
Data Index: 5550094 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.5053. Min Act: -0.1700
Data Index: 8651288 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9902. Min Range: -3.9902
Max Act: 3.4583. Min Act: -0.1700
Data Index: 7061508 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19