Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.6308. Min Act: -0.1700
Data Index: 2099509 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.4433. Min Act: -0.1700
Data Index: 4595118 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.3808. Min Act: -0.1700
Data Index: 7242809 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.3183. Min Act: -0.1700
Data Index: 3239803 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.3183. Min Act: -0.1700
Data Index: 6683883 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.2558. Min Act: -0.1700
Data Index: 5205180 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.2558. Min Act: -0.1700
Data Index: 7737278 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.2558. Min Act: -0.1700
Data Index: 8549176 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.1308. Min Act: -0.1700
Data Index: 417133 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.1308. Min Act: -0.1700
Data Index: 7207395 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.1308. Min Act: -0.1700
Data Index: 2870994 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.1308. Min Act: -0.1700
Data Index: 3646887 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.0996. Min Act: -0.1700
Data Index: 1777028 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.0996. Min Act: -0.1700
Data Index: 8813231 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.0996. Min Act: -0.1700
Data Index: 4231451 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.0371. Min Act: -0.1700
Data Index: 6906424 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.0683. Min Act: -0.1700
Data Index: 4496572 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.0683. Min Act: -0.1700
Data Index: 2025417 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6308. Min Range: -6.6308
Max Act: 6.0058. Min Act: -0.1700
Data Index: 4727926 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6308. Min Range: -6.6308
Max Act: 5.9746. Min Act: -0.1700
Data Index: 7034508 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19