Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6381 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0130. Min Range: -6.0130
Max Act: 6.0130. Min Act: -0.1700
Data Index: 4265328 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.9505. Min Act: -0.1700
Data Index: 7200433 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.8880. Min Act: -0.1700
Data Index: 5481573 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.8568. Min Act: -0.1700
Data Index: 8256962 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.7630. Min Act: -0.1700
Data Index: 5584501 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.7318. Min Act: -0.1700
Data Index: 1774890 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.7630. Min Act: -0.1700
Data Index: 1642692 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.7318. Min Act: -0.1700
Data Index: 4380853 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.7005. Min Act: -0.1700
Data Index: 4315528 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.6693. Min Act: -0.1700
Data Index: 7896760 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.5755. Min Act: -0.1700
Data Index: 8197047 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.5755. Min Act: -0.1700
Data Index: 4299896 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.5755. Min Act: -0.1700
Data Index: 8454014 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.5443. Min Act: -0.1700
Data Index: 982034 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.4818. Min Act: -0.1700
Data Index: 3789872 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.5130. Min Act: -0.1700
Data Index: 8756727 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.4818. Min Act: -0.1700
Data Index: 8665057 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.4818. Min Act: -0.1700
Data Index: 5541300 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.4818. Min Act: -0.1700
Data Index: 4405425 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0130. Min Range: -6.0130
Max Act: 5.4505. Min Act: -0.1700
Data Index: 7121781 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19