Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.9508. Min Act: -0.1700
Data Index: 6676418 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.8571. Min Act: -0.1700
Data Index: 4425791 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.6696. Min Act: -0.1700
Data Index: 937391 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.6696. Min Act: -0.1700
Data Index: 7393999 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.6696. Min Act: -0.1700
Data Index: 6973896 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.6071. Min Act: -0.1700
Data Index: 3880398 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.6071. Min Act: -0.1700
Data Index: 3143053 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.5133. Min Act: -0.1700
Data Index: 6676420 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.4821. Min Act: -0.1700
Data Index: 6316876 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.4508. Min Act: -0.1700
Data Index: 2565852 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.4196. Min Act: -0.1700
Data Index: 6606042 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.4196. Min Act: -0.1700
Data Index: 2194587 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3883. Min Act: -0.1700
Data Index: 6531407 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3883. Min Act: -0.1700
Data Index: 5068458 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3883. Min Act: -0.1700
Data Index: 3045033 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3571. Min Act: -0.1700
Data Index: 867205 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3571. Min Act: -0.1700
Data Index: 3283789 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3571. Min Act: -0.1700
Data Index: 312066 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3258. Min Act: -0.1700
Data Index: 1465981 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9508. Min Range: -6.9508
Max Act: 6.3258. Min Act: -0.1700
Data Index: 2894984 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19