Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.5277. Min Act: -0.1700
Data Index: 2092643 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.3714. Min Act: -0.1700
Data Index: 7171497 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.1839. Min Act: -0.1700
Data Index: 4740243 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.0277. Min Act: -0.1700
Data Index: 2510682 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6394497 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.0277. Min Act: -0.1700
Data Index: 3867230 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.9652. Min Act: -0.1700
Data Index: 4986625 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.9652. Min Act: -0.1700
Data Index: 4740252 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.9027. Min Act: -0.1700
Data Index: 1249463 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.9027. Min Act: -0.1700
Data Index: 7590996 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8714. Min Act: -0.1700
Data Index: 4161626 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8714. Min Act: -0.1700
Data Index: 6220676 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 5679863 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 2909015 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5994111 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 7945349 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8089. Min Act: -0.1700
Data Index: 7731849 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8089. Min Act: -0.1700
Data Index: 1728771 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7464. Min Act: -0.1700
Data Index: 2419085 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8089. Min Act: -0.1700
Data Index: 4076814 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19