Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2111. Min Range: -8.2111
Max Act: 8.2111. Min Act: -0.1700
Data Index: 2794057 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2111. Min Range: -8.2111
Max Act: 8.0861. Min Act: -0.1700
Data Index: 1462907 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.9611. Min Act: -0.1700
Data Index: 2050682 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.8986. Min Act: -0.1700
Data Index: 2212888 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.8361. Min Act: -0.1700
Data Index: 7117042 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.8986. Min Act: -0.1700
Data Index: 3239535 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.8361. Min Act: -0.1700
Data Index: 8753887 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.7736. Min Act: -0.1700
Data Index: 7882477 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.7736. Min Act: -0.1700
Data Index: 594715 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.7736. Min Act: -0.1700
Data Index: 7995858 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.6486. Min Act: -0.1700
Data Index: 1113901 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.6486. Min Act: -0.1700
Data Index: 5315024 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.6486. Min Act: -0.1700
Data Index: 791455 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.6486. Min Act: -0.1700
Data Index: 930011 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.5861. Min Act: -0.1700
Data Index: 5563638 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.6486. Min Act: -0.1700
Data Index: 7019596 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.5861. Min Act: -0.1700
Data Index: 6210724 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.5861. Min Act: -0.1700
Data Index: 4312342 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.5861. Min Act: -0.1700
Data Index: 355032 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2111. Min Range: -8.2111
Max Act: 7.5861. Min Act: -0.1700
Data Index: 2985194 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19