Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4799. Min Range: -8.4799
Max Act: 8.4799. Min Act: -0.1700
Data Index: 3791294 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4799. Min Range: -8.4799
Max Act: 8.3549. Min Act: -0.1700
Data Index: 3264660 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4799. Min Range: -8.4799
Max Act: 8.2611. Min Act: -0.1700
Data Index: 7975877 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4799. Min Range: -8.4799
Max Act: 8.1986. Min Act: -0.1700
Data Index: 8002790 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4799. Min Range: -8.4799
Max Act: 8.0736. Min Act: -0.1700
Data Index: 6609381 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.9799. Min Act: -0.1700
Data Index: 7407848 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.9486. Min Act: -0.1700
Data Index: 522294 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.9486. Min Act: -0.1700
Data Index: 4881333 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.8861. Min Act: -0.1700
Data Index: 609448 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.8861. Min Act: -0.1700
Data Index: 3424695 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.8549. Min Act: -0.1700
Data Index: 366479 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.8236. Min Act: -0.1700
Data Index: 5761549 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.7611. Min Act: -0.1700
Data Index: 2711309 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.7924. Min Act: -0.1700
Data Index: 4943988 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.7611. Min Act: -0.1700
Data Index: 1794633 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.7611. Min Act: -0.1700
Data Index: 1133986 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.7611. Min Act: -0.1700
Data Index: 1565046 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.7299. Min Act: -0.1700
Data Index: 101487 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.7299. Min Act: -0.1700
Data Index: 6506659 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4799. Min Range: -8.4799
Max Act: 7.6986. Min Act: -0.1700
Data Index: 433385 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19