Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.5473. Min Act: -0.1700
Data Index: 2508562 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.5160. Min Act: -0.1700
Data Index: 6318639 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.5160. Min Act: -0.1700
Data Index: 2883642 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.4848. Min Act: -0.1700
Data Index: 2046362 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.4535. Min Act: -0.1700
Data Index: 6388832 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.4848. Min Act: -0.1700
Data Index: 5354782 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.4223. Min Act: -0.1700
Data Index: 8095397 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.4223. Min Act: -0.1700
Data Index: 1174091 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.3285. Min Act: -0.1700
Data Index: 6527151 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.3285. Min Act: -0.1700
Data Index: 3284042 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.2660. Min Act: -0.1700
Data Index: 5067278 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.2035. Min Act: -0.1700
Data Index: 6982639 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.2035. Min Act: -0.1700
Data Index: 5846695 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.2348. Min Act: -0.1700
Data Index: 4018844 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.2035. Min Act: -0.1700
Data Index: 8397200 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.1723. Min Act: -0.1700
Data Index: 3963891 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.1723. Min Act: -0.1700
Data Index: 727642 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.1723. Min Act: -0.1700
Data Index: 1225792 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.1723. Min Act: -0.1700
Data Index: 6165743 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5473. Min Range: -5.5473
Max Act: 5.1410. Min Act: -0.1700
Data Index: 5041466 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19