Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.4330. Min Act: -0.1700
Data Index: 5774669 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.3705. Min Act: -0.1700
Data Index: 5484211 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.3705. Min Act: -0.1700
Data Index: 1593032 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.3705. Min Act: -0.1700
Data Index: 1473459 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.3080. Min Act: -0.1700
Data Index: 8695276 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.2455. Min Act: -0.1700
Data Index: 6085201 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.1830. Min Act: -0.1700
Data Index: 5256531 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.2455. Min Act: -0.1700
Data Index: 1721137 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.2455. Min Act: -0.1700
Data Index: 5248545 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.1830. Min Act: -0.1700
Data Index: 6127296 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.1830. Min Act: -0.1700
Data Index: 6081973 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.1830. Min Act: -0.1700
Data Index: 4631843 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.1205. Min Act: -0.1700
Data Index: 2161012 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.1205. Min Act: -0.1700
Data Index: 2240967 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.1205. Min Act: -0.1700
Data Index: 5910016 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.0580. Min Act: -0.1700
Data Index: 483830 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.0580. Min Act: -0.1700
Data Index: 7425676 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.0580. Min Act: -0.1700
Data Index: 7393616 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.0580. Min Act: -0.1700
Data Index: 6032529 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4330. Min Range: -8.4330
Max Act: 8.0580. Min Act: -0.1700
Data Index: 6609281 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19