Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4337 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.9890. Min Act: -0.1700
Data Index: 8670660 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.9577. Min Act: -0.1700
Data Index: 2807323 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.9577. Min Act: -0.1700
Data Index: 1744835 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.9265. Min Act: -0.1700
Data Index: 6157025 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8952. Min Act: -0.1700
Data Index: 3091162 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.9265. Min Act: -0.1698
Data Index: 7290478 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8952. Min Act: -0.1700
Data Index: 3993187 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.9265. Min Act: -0.1700
Data Index: 6747101 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8952. Min Act: -0.1700
Data Index: 2068281 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8952. Min Act: -0.1699
Data Index: 6840310 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8327. Min Act: -0.1700
Data Index: 2183877 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8640. Min Act: -0.1700
Data Index: 6997788 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8640. Min Act: -0.1700
Data Index: 3713704 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8640. Min Act: -0.1700
Data Index: 7655583 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8327. Min Act: -0.1700
Data Index: 1743539 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8327. Min Act: -0.1700
Data Index: 1944954 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8327. Min Act: -0.1700
Data Index: 5106913 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8015. Min Act: -0.1700
Data Index: 4735168 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8327. Min Act: -0.1700
Data Index: 754664 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9890. Min Range: -5.9890
Max Act: 5.8327. Min Act: -0.1700
Data Index: 4588614 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19