Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3784. Min Range: -7.3784
Max Act: 7.3784. Min Act: -0.1700
Data Index: 7730848 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3784. Min Range: -7.3784
Max Act: 7.1596. Min Act: -0.1700
Data Index: 8476666 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3784. Min Range: -7.3784
Max Act: 7.0034. Min Act: -0.1700
Data Index: 8211746 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.9721. Min Act: -0.1700
Data Index: 4556574 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.9721. Min Act: -0.1700
Data Index: 7268269 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.9721. Min Act: -0.1700
Data Index: 8402810 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.9409. Min Act: -0.1700
Data Index: 7323386 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.9409. Min Act: -0.1700
Data Index: 1433566 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.9096. Min Act: -0.1700
Data Index: 3236992 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.9096. Min Act: -0.1700
Data Index: 4968076 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.8784. Min Act: -0.1700
Data Index: 7841560 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.8784. Min Act: -0.1700
Data Index: 488290 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.8471. Min Act: -0.1700
Data Index: 7736130 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.7846. Min Act: -0.1700
Data Index: 2763272 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.8159. Min Act: -0.1700
Data Index: 6902497 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.7846. Min Act: -0.1700
Data Index: 5114214 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.7846. Min Act: -0.1700
Data Index: 8687689 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.7846. Min Act: -0.1700
Data Index: 4654169 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.7534. Min Act: -0.1700
Data Index: 6335867 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3784. Min Range: -7.3784
Max Act: 6.7534. Min Act: -0.1700
Data Index: 3195718 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19