Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1381 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0821. Min Range: -6.0821
Max Act: 6.0821. Min Act: -0.1700
Data Index: 133348 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.9258. Min Act: -0.1700
Data Index: 275705 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.9258. Min Act: -0.1700
Data Index: 6747786 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.8633. Min Act: -0.1700
Data Index: 2366441 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.8008. Min Act: -0.1700
Data Index: 5090455 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.8321. Min Act: -0.1700
Data Index: 5200763 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.8008. Min Act: -0.1700
Data Index: 1751553 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.8008. Min Act: -0.1700
Data Index: 7127332 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.7383. Min Act: -0.1700
Data Index: 2418648 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.7383. Min Act: -0.1700
Data Index: 4502377 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3936933 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.7071. Min Act: -0.1700
Data Index: 7463142 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 2374019 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 4289984 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6418171 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 6100682 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 2496779 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 795737 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 2790333 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0821. Min Range: -6.0821
Max Act: 5.6758. Min Act: -0.1700
Data Index: 7173433 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19