Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 776 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.8591. Min Act: -0.1700
Data Index: 312852 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.8278. Min Act: -0.1700
Data Index: 4961161 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7653. Min Act: -0.1700
Data Index: 7236287 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7653. Min Act: -0.1700
Data Index: 5555486 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7341. Min Act: -0.1700
Data Index: 3866916 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7028. Min Act: -0.1700
Data Index: 7367568 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7341. Min Act: -0.1700
Data Index: 198590 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7341. Min Act: -0.1700
Data Index: 776136 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7028. Min Act: -0.1700
Data Index: 6568578 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7028. Min Act: -0.1700
Data Index: 7262378 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6716. Min Act: -0.1700
Data Index: 5485678 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7028. Min Act: -0.1700
Data Index: 5939633 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6716. Min Act: -0.1700
Data Index: 2735524 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.7028. Min Act: -0.1700
Data Index: 2704620 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6403. Min Act: -0.1700
Data Index: 5775790 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6403. Min Act: -0.1700
Data Index: 8223626 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6403. Min Act: -0.1700
Data Index: 980330 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6403. Min Act: -0.1700
Data Index: 342682 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6403. Min Act: -0.1700
Data Index: 6649583 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8591. Min Range: -5.8591
Max Act: 5.6403. Min Act: -0.1700
Data Index: 2231742 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19