Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 208 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.2392. Min Act: -0.1700
Data Index: 7114902 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.1767. Min Act: -0.1700
Data Index: 8127025 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.1455. Min Act: -0.1700
Data Index: 8730892 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.1455. Min Act: -0.1700
Data Index: 4255786 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.1455. Min Act: -0.1700
Data Index: 6018280 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.1142. Min Act: -0.1700
Data Index: 4010535 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.1142. Min Act: -0.1700
Data Index: 6005241 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.0830. Min Act: -0.1700
Data Index: 8305052 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.0830. Min Act: -0.1700
Data Index: 491258 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.0517. Min Act: -0.1700
Data Index: 1353076 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2392. Min Range: -7.2392
Max Act: 7.0205. Min Act: -0.1700
Data Index: 7567973 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.9892. Min Act: -0.1700
Data Index: 109558 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.9580. Min Act: -0.1700
Data Index: 3932993 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.9267. Min Act: -0.1700
Data Index: 6912147 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.8955. Min Act: -0.1700
Data Index: 1728637 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.8955. Min Act: -0.1700
Data Index: 4966714 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.8955. Min Act: -0.1700
Data Index: 3015508 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.8642. Min Act: -0.1700
Data Index: 4883937 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.8642. Min Act: -0.1700
Data Index: 426700 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2392. Min Range: -7.2392
Max Act: 6.8642. Min Act: -0.1700
Data Index: 6633287 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19