Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.8979. Min Act: -0.1700
Data Index: 5395925 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.7729. Min Act: -0.1700
Data Index: 835083 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.7417. Min Act: -0.1700
Data Index: 2650594 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.5542. Min Act: -0.1700
Data Index: 5512199 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.5542. Min Act: -0.1700
Data Index: 2221666 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.4917. Min Act: -0.1700
Data Index: 4018099 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.5229. Min Act: -0.1700
Data Index: 2508175 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.4917. Min Act: -0.1700
Data Index: 1449917 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.4604. Min Act: -0.1700
Data Index: 7155672 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.3979. Min Act: -0.1700
Data Index: 1839924 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.3042. Min Act: -0.1700
Data Index: 8144247 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.2729. Min Act: -0.1700
Data Index: 5688536 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.2417. Min Act: -0.1700
Data Index: 1256788 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.2417. Min Act: -0.1700
Data Index: 3184892 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.1479. Min Act: -0.1700
Data Index: 5083163 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.1479. Min Act: -0.1700
Data Index: 8094202 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.1792. Min Act: -0.1700
Data Index: 8442741 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.1479. Min Act: -0.1700
Data Index: 1056281 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.1167. Min Act: -0.1700
Data Index: 3359114 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8979. Min Range: -6.8979
Max Act: 6.0542. Min Act: -0.1700
Data Index: 5510183 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19