Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 740 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2891. Min Range: -8.2891
Max Act: 8.2891. Min Act: -0.1700
Data Index: 1191294 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2891. Min Range: -8.2891
Max Act: 8.1641. Min Act: -0.1700
Data Index: 6322997 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2891. Min Range: -8.2891
Max Act: 8.1016. Min Act: -0.1700
Data Index: 3321799 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2891. Min Range: -8.2891
Max Act: 8.1016. Min Act: -0.1700
Data Index: 2513697 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2891. Min Range: -8.2891
Max Act: 8.1016. Min Act: -0.1700
Data Index: 8601834 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2891. Min Range: -8.2891
Max Act: 8.0391. Min Act: -0.1700
Data Index: 4058621 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2891. Min Range: -8.2891
Max Act: 8.0391. Min Act: -0.1700
Data Index: 247286 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9766. Min Act: -0.1700
Data Index: 4272740 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9766. Min Act: -0.1700
Data Index: 6043209 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9766. Min Act: -0.1700
Data Index: 416615 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9141. Min Act: -0.1700
Data Index: 6226999 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9141. Min Act: -0.1700
Data Index: 428179 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9766. Min Act: -0.1700
Data Index: 1601343 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9141. Min Act: -0.1700
Data Index: 3165174 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9141. Min Act: -0.1700
Data Index: 5432015 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.9141. Min Act: -0.1700
Data Index: 5958790 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.8516. Min Act: -0.1700
Data Index: 5136901 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.8203. Min Act: -0.1700
Data Index: 2473626 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.8516. Min Act: -0.1700
Data Index: 1890521 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2891. Min Range: -8.2891
Max Act: 7.7891. Min Act: -0.1700
Data Index: 6258282 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19