Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.6810. Min Act: -0.1700
Data Index: 1296837 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.5247. Min Act: -0.1700
Data Index: 3643386 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.4622. Min Act: -0.1700
Data Index: 90529 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.4310. Min Act: -0.1700
Data Index: 7065688 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.3997. Min Act: -0.1700
Data Index: 2685255 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.3685. Min Act: -0.1700
Data Index: 123457 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.3372. Min Act: -0.1700
Data Index: 8475188 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.3060. Min Act: -0.1700
Data Index: 1728772 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.2747. Min Act: -0.1700
Data Index: 5663807 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.3060. Min Act: -0.1700
Data Index: 3376353 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.3060. Min Act: -0.1700
Data Index: 5546621 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.3060. Min Act: -0.1700
Data Index: 8700445 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.2435. Min Act: -0.1700
Data Index: 4609835 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.2435. Min Act: -0.1700
Data Index: 2788606 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.2122. Min Act: -0.1700
Data Index: 3093854 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.2122. Min Act: -0.1700
Data Index: 7305633 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.1810. Min Act: -0.1700
Data Index: 3910023 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.1810. Min Act: -0.1700
Data Index: 3190153 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.1497. Min Act: -0.1700
Data Index: 1782797 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6810. Min Range: -6.6810
Max Act: 6.1497. Min Act: -0.1700
Data Index: 7821007 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19