Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1916 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.6828. Min Act: -0.1700
Data Index: 4558697 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.5266. Min Act: -0.1700
Data Index: 6399649 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4953. Min Act: -0.1700
Data Index: 1219395 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4953. Min Act: -0.1700
Data Index: 377323 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4328. Min Act: -0.1700
Data Index: 5417114 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.4016. Min Act: -0.1700
Data Index: 1180063 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3078. Min Act: -0.1700
Data Index: 7492707 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3391. Min Act: -0.1700
Data Index: 8510546 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.3078. Min Act: -0.1700
Data Index: 3235359 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2766. Min Act: -0.1700
Data Index: 7056473 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2453. Min Act: -0.1700
Data Index: 2587890 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2141. Min Act: -0.1700
Data Index: 8200843 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2141. Min Act: -0.1700
Data Index: 2477944 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.2141. Min Act: -0.1700
Data Index: 395299 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.1828. Min Act: -0.1700
Data Index: 7418887 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.1828. Min Act: -0.1700
Data Index: 7797698 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.1828. Min Act: -0.1700
Data Index: 439613 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.1828. Min Act: -0.1700
Data Index: 2124163 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.1516. Min Act: -0.1700
Data Index: 4749733 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6828. Min Range: -5.6828
Max Act: 5.1516. Min Act: -0.1700
Data Index: 5351472 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19