Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2885 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3497. Min Range: -8.3497
Max Act: 8.3497. Min Act: -0.1700
Data Index: 6363497 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3497. Min Range: -8.3497
Max Act: 8.0372. Min Act: -0.1700
Data Index: 3328130 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3497. Min Range: -8.3497
Max Act: 8.0372. Min Act: -0.1700
Data Index: 8625258 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.9747. Min Act: -0.1700
Data Index: 8293078 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.9747. Min Act: -0.1700
Data Index: 8763486 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.9122. Min Act: -0.1700
Data Index: 4649758 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.9122. Min Act: -0.1700
Data Index: 6857595 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.9122. Min Act: -0.1700
Data Index: 7064730 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.9122. Min Act: -0.1700
Data Index: 4163666 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.8497. Min Act: -0.1700
Data Index: 7287827 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.8497. Min Act: -0.1700
Data Index: 631711 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.8497. Min Act: -0.1700
Data Index: 4822289 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.9122. Min Act: -0.1700
Data Index: 5734742 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.7872. Min Act: -0.1700
Data Index: 1900794 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.7247. Min Act: -0.1699
Data Index: 982500 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.6309. Min Act: -0.1700
Data Index: 4552318 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.6622. Min Act: -0.1700
Data Index: 7651937 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.6622. Min Act: -0.1700
Data Index: 5638286 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.6622. Min Act: -0.1700
Data Index: 3957427 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3497. Min Range: -8.3497
Max Act: 7.5997. Min Act: -0.1700
Data Index: 7246720 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19