Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1409 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.7391. Min Act: -0.1700
Data Index: 8803870 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.6766. Min Act: -0.1700
Data Index: 2672521 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.5516. Min Act: -0.1700
Data Index: 3263096 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.5204. Min Act: -0.1700
Data Index: 5878880 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.4891. Min Act: -0.1700
Data Index: 7083488 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.4266. Min Act: -0.1700
Data Index: 1773903 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.3329. Min Act: -0.1700
Data Index: 2458718 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.2704. Min Act: -0.1700
Data Index: 448601 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.2391. Min Act: -0.1700
Data Index: 477565 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.2079. Min Act: -0.1700
Data Index: 4929730 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.2079. Min Act: -0.1700
Data Index: 8027065 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.1454. Min Act: -0.1700
Data Index: 1045604 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.1141. Min Act: -0.1700
Data Index: 4889914 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.1141. Min Act: -0.1700
Data Index: 2760642 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.1141. Min Act: -0.1700
Data Index: 7023542 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.0829. Min Act: -0.1700
Data Index: 6828514 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 8508054 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 1019463 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 6538182 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7391. Min Range: -6.7391
Max Act: 6.0516. Min Act: -0.1700
Data Index: 5016714 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19