Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2121 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0642. Min Range: -7.0642
Max Act: 7.0642. Min Act: -0.1700
Data Index: 5738645 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.8454. Min Act: -0.1700
Data Index: 1538095 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.7829. Min Act: -0.1700
Data Index: 309452 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.7204. Min Act: -0.1700
Data Index: 4904847 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.6892. Min Act: -0.1700
Data Index: 5124725 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.6267. Min Act: -0.1700
Data Index: 7975571 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5954. Min Act: -0.1700
Data Index: 6012544 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5954. Min Act: -0.1700
Data Index: 5486862 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5642. Min Act: -0.1700
Data Index: 3282849 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5954. Min Act: -0.1700
Data Index: 7997443 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5642. Min Act: -0.1700
Data Index: 3187929 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5329. Min Act: -0.1700
Data Index: 7647512 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5017. Min Act: -0.1700
Data Index: 197979 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5017. Min Act: -0.1700
Data Index: 206732 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.4704. Min Act: -0.1700
Data Index: 6407988 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.4704. Min Act: -0.1700
Data Index: 1584625 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.5017. Min Act: -0.1700
Data Index: 2570827 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.4392. Min Act: -0.1700
Data Index: 6696030 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.4704. Min Act: -0.1700
Data Index: 2796053 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0642. Min Range: -7.0642
Max Act: 6.3767. Min Act: -0.1700
Data Index: 1483341 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19