Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1229 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1747. Min Range: -8.1747
Max Act: 8.1747. Min Act: -0.1700
Data Index: 2238966 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.7059. Min Act: -0.1700
Data Index: 4918796 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.5184. Min Act: -0.1700
Data Index: 1260891 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.4247. Min Act: -0.1700
Data Index: 4515618 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.3934. Min Act: -0.1700
Data Index: 8514932 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.2684. Min Act: -0.1700
Data Index: 8564653 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.2684. Min Act: -0.1700
Data Index: 2624013 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.2684. Min Act: -0.1700
Data Index: 5714087 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.2372. Min Act: -0.1700
Data Index: 7639937 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.1747. Min Act: -0.1700
Data Index: 1016494 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.1747. Min Act: -0.1700
Data Index: 33941 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.1122. Min Act: -0.1700
Data Index: 2158870 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0809. Min Act: -0.1700
Data Index: 8475142 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0809. Min Act: -0.1700
Data Index: 8136651 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0809. Min Act: -0.1700
Data Index: 755366 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 5457929 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 4636112 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 6139698 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 6322554 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1747. Min Range: -8.1747
Max Act: 7.0184. Min Act: -0.1700
Data Index: 3870058 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19