Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.3496. Min Act: -0.1700
Data Index: 3345371 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.2871. Min Act: -0.1700
Data Index: 2980148 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.2558. Min Act: -0.1700
Data Index: 6634567 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.2558. Min Act: -0.1700
Data Index: 2824825 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.2246. Min Act: -0.1700
Data Index: 8513671 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0995. Min Act: -0.1700
Data Index: 3242174 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0995. Min Act: -0.1700
Data Index: 6815538 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0995. Min Act: -0.1700
Data Index: 5540935 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0995. Min Act: -0.1700
Data Index: 6822514 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0995. Min Act: -0.1700
Data Index: 1383576 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0683. Min Act: -0.1700
Data Index: 1027412 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0683. Min Act: -0.1700
Data Index: 3148382 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0370. Min Act: -0.1700
Data Index: 3430900 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0683. Min Act: -0.1700
Data Index: 7168564 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0058. Min Act: -0.1700
Data Index: 5746748 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0058. Min Act: -0.1700
Data Index: 2323548 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3496. Min Range: -4.3496
Max Act: 3.9745. Min Act: -0.1700
Data Index: 6232595 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3496. Min Range: -4.3496
Max Act: 3.9745. Min Act: -0.1700
Data Index: 964248 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3496. Min Range: -4.3496
Max Act: 4.0058. Min Act: -0.1700
Data Index: 3043773 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3496. Min Range: -4.3496
Max Act: 3.9745. Min Act: -0.1700
Data Index: 3214654 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19