Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1506 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1376. Min Range: -6.1376
Max Act: 6.1376. Min Act: -0.1700
Data Index: 3303558 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1376. Min Range: -6.1376
Max Act: 6.1376. Min Act: -0.1700
Data Index: 4054286 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.9501. Min Act: -0.1700
Data Index: 471781 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.9501. Min Act: -0.1700
Data Index: 8745555 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.9188. Min Act: -0.1700
Data Index: 8731884 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.9188. Min Act: -0.1700
Data Index: 2034156 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.8563. Min Act: -0.1700
Data Index: 325039 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.8563. Min Act: -0.1700
Data Index: 675747 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7938. Min Act: -0.1700
Data Index: 6448988 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7938. Min Act: -0.1700
Data Index: 7929232 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.8251. Min Act: -0.1700
Data Index: 4821794 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7938. Min Act: -0.1700
Data Index: 5057260 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7938. Min Act: -0.1700
Data Index: 7833041 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7938. Min Act: -0.1700
Data Index: 1943202 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7626. Min Act: -0.1700
Data Index: 4965794 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7626. Min Act: -0.1700
Data Index: 8571712 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7626. Min Act: -0.1700
Data Index: 6380832 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5507610 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7001. Min Act: -0.1700
Data Index: 2229530 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1376. Min Range: -6.1376
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5514492 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19