Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.3405. Min Act: -0.1700
Data Index: 3348237 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.3241. Min Act: -0.1700
Data Index: 6065106 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.3076. Min Act: -0.1700
Data Index: 6159349 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.3076. Min Act: -0.1700
Data Index: 8297740 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.3076. Min Act: -0.1700
Data Index: 3237011 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2912. Min Act: -0.1700
Data Index: 3825143 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2582. Min Act: -0.1700
Data Index: 6059454 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2582. Min Act: -0.1698
Data Index: 5332577 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2582. Min Act: -0.1700
Data Index: 3324683 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2417. Min Act: -0.1700
Data Index: 5820833 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2417. Min Act: -0.1700
Data Index: 3178202 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2251. Min Act: -0.1700
Data Index: 1177232 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2251. Min Act: -0.1700
Data Index: 2901831 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2251. Min Act: -0.1700
Data Index: 5491308 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2086. Min Act: -0.1700
Data Index: 2208374 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1920. Min Act: -0.1700
Data Index: 3982241 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2086. Min Act: -0.1697
Data Index: 3825142 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.2086. Min Act: -0.1700
Data Index: 7003275 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1754. Min Act: -0.1700
Data Index: 5737383 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3405. Min Range: -2.3405
Max Act: 2.1920. Min Act: -0.1700
Data Index: 3526052 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19