Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1891. Min Range: -7.1891
Max Act: 7.1891. Min Act: -0.1700
Data Index: 8551582 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1891. Min Range: -7.1891
Max Act: 7.1266. Min Act: -0.1700
Data Index: 1047533 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1891. Min Range: -7.1891
Max Act: 7.0641. Min Act: -0.1700
Data Index: 5134051 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1891. Min Range: -7.1891
Max Act: 7.0329. Min Act: -0.1700
Data Index: 1543140 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.9079. Min Act: -0.1700
Data Index: 1702373 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.6891. Min Act: -0.1700
Data Index: 4140661 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.6891. Min Act: -0.1700
Data Index: 1911652 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.6266. Min Act: -0.1700
Data Index: 5377873 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.5954. Min Act: -0.1700
Data Index: 4773286 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.5954. Min Act: -0.1700
Data Index: 7232581 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.5954. Min Act: -0.1700
Data Index: 5987370 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.5329. Min Act: -0.1700
Data Index: 6066066 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.5329. Min Act: -0.1700
Data Index: 7507307 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.4704. Min Act: -0.1700
Data Index: 1931270 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.5016. Min Act: -0.1700
Data Index: 3676945 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.4704. Min Act: -0.1700
Data Index: 2472576 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.4704. Min Act: -0.1700
Data Index: 8527004 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.4391. Min Act: -0.1700
Data Index: 5027881 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.3766. Min Act: -0.1700
Data Index: 7020639 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1891. Min Range: -7.1891
Max Act: 6.3766. Min Act: -0.1700
Data Index: 5206000 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19