Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5898. Min Range: -8.5898
Max Act: 8.5898. Min Act: -0.1700
Data Index: 5237061 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5898. Min Range: -8.5898
Max Act: 8.0273. Min Act: -0.1700
Data Index: 5321086 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.8398. Min Act: -0.1700
Data Index: 3708095 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.7773. Min Act: -0.1700
Data Index: 7537453 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.7461. Min Act: -0.1700
Data Index: 2091831 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.5586. Min Act: -0.1700
Data Index: 954518 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.5273. Min Act: -0.1700
Data Index: 8560536 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.4648. Min Act: -0.1700
Data Index: 3442819 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.4336. Min Act: -0.1700
Data Index: 1122162 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.4023. Min Act: -0.1700
Data Index: 1964698 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.4023. Min Act: -0.1700
Data Index: 1101714 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.3711. Min Act: -0.1700
Data Index: 4930218 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.3398. Min Act: -0.1700
Data Index: 4874711 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.3398. Min Act: -0.1700
Data Index: 2941686 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.3086. Min Act: -0.1700
Data Index: 6101753 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.3086. Min Act: -0.1700
Data Index: 2205470 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.3086. Min Act: -0.1700
Data Index: 8451678 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.2773. Min Act: -0.1700
Data Index: 840116 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.2773. Min Act: -0.1700
Data Index: 5335966 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5898. Min Range: -8.5898
Max Act: 7.2461. Min Act: -0.1700
Data Index: 5866949 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19