Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5149 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.3607. Min Act: -0.1700
Data Index: 4178464 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.3294. Min Act: -0.1700
Data Index: 7954788 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.2982. Min Act: -0.1700
Data Index: 3554349 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.1732. Min Act: -0.1700
Data Index: 6620462 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.1732. Min Act: -0.1700
Data Index: 1012193 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.0482. Min Act: -0.1700
Data Index: 7689599 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.0482. Min Act: -0.1700
Data Index: 4732597 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.0169. Min Act: -0.1700
Data Index: 1302235 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.0794. Min Act: -0.1700
Data Index: 6000132 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3607. Min Range: -5.3607
Max Act: 5.0169. Min Act: -0.1700
Data Index: 1069862 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9857. Min Act: -0.1700
Data Index: 2539047 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9857. Min Act: -0.1699
Data Index: 3858451 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9544. Min Act: -0.1700
Data Index: 3564502 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9857. Min Act: -0.1700
Data Index: 2539048 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9544. Min Act: -0.1700
Data Index: 3645426 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9544. Min Act: -0.1700
Data Index: 5382192 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9544. Min Act: -0.1700
Data Index: 3083605 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9544. Min Act: -0.1700
Data Index: 6649090 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9232. Min Act: -0.1700
Data Index: 7354785 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3607. Min Range: -5.3607
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6871523 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19