Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 53 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.7196. Min Act: -0.1700
Data Index: 7978042 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.6571. Min Act: -0.1700
Data Index: 3863560 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.5321. Min Act: -0.1700
Data Index: 3214861 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.5008. Min Act: -0.1700
Data Index: 4069966 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.5008. Min Act: -0.1700
Data Index: 7131837 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.5008. Min Act: -0.1700
Data Index: 7593602 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.4696. Min Act: -0.1700
Data Index: 278215 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.4696. Min Act: -0.1700
Data Index: 5427265 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.4071. Min Act: -0.1700
Data Index: 7818900 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.4383. Min Act: -0.1700
Data Index: 3823098 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.4383. Min Act: -0.1700
Data Index: 6882850 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3758. Min Act: -0.1700
Data Index: 7028648 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3758. Min Act: -0.1700
Data Index: 850907 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3758. Min Act: -0.1700
Data Index: 8766542 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3446. Min Act: -0.1700
Data Index: 3863559 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3446. Min Act: -0.1700
Data Index: 4039674 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3133. Min Act: -0.1700
Data Index: 1006130 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3133. Min Act: -0.1700
Data Index: 5532900 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3133. Min Act: -0.1700
Data Index: 6882844 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7196. Min Range: -5.7196
Max Act: 5.3133. Min Act: -0.1700
Data Index: 3429841 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19