Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3908 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 5673838 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 8317086 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 8076432 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 7629759 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 1467348 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 610498 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 7608291 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 507387 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 6009423 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 1258774 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 1930652 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 4786519 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 4677251 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 475373 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 3287710 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 2838207 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 2783265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 748460 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 2225984 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0188. Min Range: -4.0188
Max Act: 4.0188. Min Act: -0.1700
Data Index: 748463 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19