Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.7556. Min Act: -0.1700
Data Index: 5218587 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.6306. Min Act: -0.1700
Data Index: 6365298 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.6618. Min Act: -0.1700
Data Index: 7959769 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.5056. Min Act: -0.1700
Data Index: 7847664 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.4743. Min Act: -0.1700
Data Index: 2738280 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.4743. Min Act: -0.1700
Data Index: 4751039 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.4743. Min Act: -0.1700
Data Index: 4206131 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.4118. Min Act: -0.1700
Data Index: 1248942 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.4118. Min Act: -0.1700
Data Index: 7980068 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.4118. Min Act: -0.1700
Data Index: 2350205 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.3181. Min Act: -0.1700
Data Index: 2248457 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.3181. Min Act: -0.1700
Data Index: 5950742 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2868. Min Act: -0.1700
Data Index: 5887793 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2868. Min Act: -0.1700
Data Index: 8342388 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2868. Min Act: -0.1700
Data Index: 6311566 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2868. Min Act: -0.1700
Data Index: 6681017 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2868. Min Act: -0.1700
Data Index: 6622732 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2556. Min Act: -0.1700
Data Index: 7913974 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2868. Min Act: -0.1700
Data Index: 4507612 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7556. Min Range: -5.7556
Max Act: 5.2556. Min Act: -0.1700
Data Index: 5202997 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19