Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.8415. Min Act: -0.1700
Data Index: 5371812 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.8103. Min Act: -0.1700
Data Index: 3286901 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.7478. Min Act: -0.1700
Data Index: 599203 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.6853. Min Act: -0.1700
Data Index: 4228803 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.6228. Min Act: -0.1700
Data Index: 8470320 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.5915. Min Act: -0.1700
Data Index: 3498973 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.5915. Min Act: -0.1700
Data Index: 4250835 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.5290. Min Act: -0.1700
Data Index: 7520005 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.4978. Min Act: -0.1700
Data Index: 7827155 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.4978. Min Act: -0.1700
Data Index: 5626864 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.4353. Min Act: -0.1700
Data Index: 212828 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.4040. Min Act: -0.1700
Data Index: 8439803 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.4040. Min Act: -0.1700
Data Index: 1644705 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.3415. Min Act: -0.1700
Data Index: 8307404 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.3415. Min Act: -0.1700
Data Index: 1907833 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.2790. Min Act: -0.1700
Data Index: 7875007 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.2478. Min Act: -0.1700
Data Index: 6836485 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.2478. Min Act: -0.1700
Data Index: 4237985 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.2165. Min Act: -0.1700
Data Index: 5029910 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8415. Min Range: -6.8415
Max Act: 6.1853. Min Act: -0.1700
Data Index: 5757647 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19