Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1779. Min Range: -6.1779
Max Act: 6.1779. Min Act: -0.1700
Data Index: 847012 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.9279. Min Act: -0.1700
Data Index: 8598836 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.8654. Min Act: -0.1700
Data Index: 7185689 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.8654. Min Act: -0.1700
Data Index: 8457146 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.8029. Min Act: -0.1700
Data Index: 790533 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.7716. Min Act: -0.1700
Data Index: 1946735 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.7404. Min Act: -0.1700
Data Index: 1879579 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.7091. Min Act: -0.1700
Data Index: 6270441 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.7091. Min Act: -0.1700
Data Index: 1012969 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.7091. Min Act: -0.1700
Data Index: 6199891 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.7091. Min Act: -0.1700
Data Index: 5882454 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6779. Min Act: -0.1700
Data Index: 2176544 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6779. Min Act: -0.1700
Data Index: 1683838 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6466. Min Act: -0.1700
Data Index: 3417867 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6466. Min Act: -0.1700
Data Index: 2675622 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6466. Min Act: -0.1700
Data Index: 4970191 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6779. Min Act: -0.1700
Data Index: 8005076 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6154. Min Act: -0.1700
Data Index: 138295 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.6154. Min Act: -0.1699
Data Index: 2954829 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1779. Min Range: -6.1779
Max Act: 5.5841. Min Act: -0.1700
Data Index: 4432425 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19