Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.6496. Min Act: -0.1700
Data Index: 3314445 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.5871. Min Act: -0.1700
Data Index: 4598578 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.5246. Min Act: -0.1700
Data Index: 6867948 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.4621. Min Act: -0.1700
Data Index: 578420 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.3996. Min Act: -0.1700
Data Index: 179756 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.2746. Min Act: -0.1700
Data Index: 1782079 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.2746. Min Act: -0.1700
Data Index: 8380146 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.0871. Min Act: -0.1700
Data Index: 200575 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.0558. Min Act: -0.1700
Data Index: 7833028 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.0871. Min Act: -0.1700
Data Index: 4189300 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6496. Min Range: -8.6496
Max Act: 8.0246. Min Act: -0.1700
Data Index: 1882293 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.9621. Min Act: -0.1700
Data Index: 5050579 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.9621. Min Act: -0.1700
Data Index: 602850 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.9308. Min Act: -0.1700
Data Index: 8741632 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.9308. Min Act: -0.1700
Data Index: 7036598 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.9308. Min Act: -0.1700
Data Index: 83724 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.8996. Min Act: -0.1700
Data Index: 4267161 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.8683. Min Act: -0.1700
Data Index: 8015652 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.8058. Min Act: -0.1700
Data Index: 6892705 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6496. Min Range: -8.6496
Max Act: 7.8371. Min Act: -0.1700
Data Index: 8809907 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19