Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.6415. Min Act: -0.1700
Data Index: 1480665 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.3915. Min Act: -0.1700
Data Index: 3335648 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.3290. Min Act: -0.1700
Data Index: 1494948 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.3915. Min Act: -0.1700
Data Index: 1009554 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.3290. Min Act: -0.1700
Data Index: 3277181 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.2665. Min Act: -0.1700
Data Index: 6093395 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.2040. Min Act: -0.1700
Data Index: 7710457 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.1415. Min Act: -0.1700
Data Index: 7844831 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.0790. Min Act: -0.1700
Data Index: 7883058 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.0790. Min Act: -0.1700
Data Index: 6133938 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6415. Min Range: -8.6415
Max Act: 8.0165. Min Act: -0.1700
Data Index: 1105962 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.9540. Min Act: -0.1700
Data Index: 5532517 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.9540. Min Act: -0.1700
Data Index: 2283334 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.9540. Min Act: -0.1700
Data Index: 390363 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.9540. Min Act: -0.1700
Data Index: 3811212 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.9228. Min Act: -0.1700
Data Index: 7777948 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.9228. Min Act: -0.1700
Data Index: 5360776 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.8915. Min Act: -0.1700
Data Index: 1924301 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.8290. Min Act: -0.1700
Data Index: 3123789 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6415. Min Range: -8.6415
Max Act: 7.7978. Min Act: -0.1700
Data Index: 2266165 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19