Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.8909. Min Act: -0.1700
Data Index: 4947602 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.9221. Min Act: -0.1700
Data Index: 3644518 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.8909. Min Act: -0.1700
Data Index: 6259135 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.7659. Min Act: -0.1700
Data Index: 1492056 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.7659. Min Act: -0.1700
Data Index: 3790768 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.7034. Min Act: -0.1700
Data Index: 3867566 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.6721. Min Act: -0.1700
Data Index: 5196555 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.6721. Min Act: -0.1700
Data Index: 7699750 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.6096. Min Act: -0.1700
Data Index: 5334340 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.6096. Min Act: -0.1700
Data Index: 49366 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.6096. Min Act: -0.1700
Data Index: 6583232 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5784. Min Act: -0.1700
Data Index: 1035700 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5784. Min Act: -0.1700
Data Index: 8832541 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5784. Min Act: -0.1700
Data Index: 512575 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5784. Min Act: -0.1700
Data Index: 6996619 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5784. Min Act: -0.1700
Data Index: 4884160 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5784. Min Act: -0.1700
Data Index: 861105 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5471. Min Act: -0.1700
Data Index: 915275 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5159. Min Act: -0.1700
Data Index: 5320471 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9221. Min Range: -4.9221
Max Act: 4.5471. Min Act: -0.1700
Data Index: 4994771 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19